© 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
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 36346
    Prev
    Next
    INDEX
    Explanations

    scientific discoveries and explorations

    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
    +0.32
    1.6%
    288
    +0.11
    0.6%
    6
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.32
    0.34
    362
    +0.11
    0.20
    608
    +0.11
    0.26
    Negative Logits
     paced
    -0.67
    wr
    -0.66
    cussion
    -0.66
    oided
    -0.65
    quote
    -0.62
    etime
    -0.60
    quet
    -0.60
    ña
    -0.60
    wrap
    -0.59
    ogun
    -0.58
    POSITIVE LOGITS
    gdala
    0.75
     flaws
    0.73
    Ô
    0.73
    æĥ
    0.71
    çīĪ
    0.69
    ibility
    0.68
     anew
    0.68
    âĸĴ
    0.66
     Lauder
    0.64
    使
    0.64
    Activations Density 13.932%

    No Known Activations