Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 45260
    Prev
    Next
    INDEX
    Explanations

    titles, names, and descriptions related to automobiles, races, funding, and legislation

    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
    236
    +0.12
    0.5%
    355
    +0.12
    0.5%
    55
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.12
    0.30
    608
    +0.12
    0.19
    509
    +0.11
    0.07
    Negative Logits
    osponsors
    -0.85
    scribe
    -0.78
    idential
    -0.76
    icker
    -0.72
    iest
    -0.68
    itable
    -0.67
    achus
    -0.66
    azed
    -0.66
    DERR
    -0.65
     Carlton
    -0.65
    POSITIVE LOGITS
     considerations
    0.95
     coupled
    0.86
    artifacts
    0.85
     factors
    0.84
     complications
    0.82
     fact
    0.81
    EVA
    0.79
    Conclusion
    0.77
     mitigating
    0.76
     inexper
    0.75
    Activations Density 13.295%

    No Known Activations