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. 45285
    Prev
    Next
    INDEX
    Explanations

    percentages and numerical data in text

    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
    +0.18
    0.9%
    718
    +0.10
    0.5%
    99
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.18
    0.20
    393
    +0.10
    0.27
    362
    +0.09
    0.12
    Negative Logits
    士
    -0.72
     Tayyip
    -0.72
    Merit
    -0.70
     Horizons
    -0.68
    IRT
    -0.66
    æ©
    -0.64
    itans
    -0.64
    ulus
    -0.64
    ÄŁ
    -0.63
    ieties
    -0.63
    POSITIVE LOGITS
    pointer
    0.74
     percentage
    0.69
     percentages
    0.68
    pointers
    0.68
     (%)
    0.67
    ttle
    0.67
     accuracy
    0.66
    hetically
    0.64
    rate
    0.63
     humidity
    0.63
    Activations Density 11.040%

    No Known Activations