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

    Neuronpedia

    APICircuit 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. 34481
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to complementing or supplementing something

    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
    +0.19
    0.8%
    459
    +0.12
    0.5%
    616
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.19
    0.21
    608
    +0.12
    0.24
    385
    +0.12
    0.20
    Negative Logits
    Blade
    -0.82
    psy
    -0.68
     Empires
    -0.67
    GER
    -0.66
    RANT
    -0.63
     Blade
    -0.62
    ves
    -0.62
    rants
    -0.62
     Roller
    -0.62
     Blades
    -0.61
    POSITIVE LOGITS
    arity
    1.13
     complement
    1.06
    ement
    1.02
    xual
    1.00
    atively
    0.90
    ements
    0.90
    ments
    0.89
    mented
    0.87
    endum
    0.87
    orously
    0.85
    Activations Density 15.007%

    No Known Activations