© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 31626
    Prev
    Next
    INDEX
    Explanations

    information related to electronic devices, especially tablets and smartphones, including details about their specifications, features, and performance

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.12
    0.9%
    459
    +0.07
    0.5%
    326
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.12
    0.33
    566
    +0.07
    0.14
    59
    +0.07
    0.08
    Negative Logits
     Amendments
    -0.44
     yourselves
    -0.44
     Negro
    -0.42
     TRANS
    -0.41
     joins
    -0.41
     cis
    -0.41
     insol
    -0.41
    emer
    -0.40
     enshr
    -0.40
    heres
    -0.40
    POSITIVE LOGITS
     testers
    0.66
    avoid
    0.51
    EStream
    0.51
     HTC
    0.51
     anecd
    0.50
    tested
    0.50
     tested
    0.48
    lvl
    0.48
     Asus
    0.48
     myself
    0.47
    Activations Density 17.327%

    No Known Activations