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. 45396
    Prev
    Next
    INDEX
    Explanations

    information related to colors and color schemes

    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
    +0.15
    0.6%
    109
    +0.13
    0.5%
    634
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.15
    0.16
    393
    +0.13
    0.22
    77
    +0.13
    0.07
    Negative Logits
    doms
    -1.18
    _-
    -0.98
    idem
    -0.97
    olicy
    -0.92
    uthor
    -0.89
    yu
    -0.82
     Cheong
    -0.79
    isSpecialOrderable
    -0.77
    uckland
    -0.77
    rolet
    -0.76
    POSITIVE LOGITS
     palette
    1.20
    blind
    1.18
     coded
    1.01
     color
    0.97
    color
    0.93
    ="#
    0.92
     colors
    0.91
    pill
    0.90
    grain
    0.90
     Spray
    0.87
    Activations Density 11.040%

    No Known Activations