© 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. 35873
    Prev
    Next
    INDEX
    Explanations

    statistics or information about specific groups or demographics

    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
    436
    +0.06
    0.5%
    391
    +0.05
    0.5%
    79
    +0.05
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    391
    +0.06
    0.02
    336
    +0.05
    0.04
    640
    +0.05
    0.22
    Negative Logits
     showc
    -0.35
     trave
    -0.31
    ELF
    -0.30
     wiser
    -0.29
     disg
    -0.29
     challeng
    -0.29
    ÃįÃį
    -0.29
     sled
    -0.28
     Yosemite
    -0.28
     deliberations
    -0.28
    POSITIVE LOGITS
    ous
    0.40
    oso
    0.38
    eless
    0.38
    olated
    0.37
    antes
    0.36
    ibilities
    0.36
    able
    0.36
    haus
    0.35
    rette
    0.35
    irgin
    0.35
    Activations Density 12.433%

    No Known Activations