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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 13518
    Prev
    Next
    INDEX
    Explanations

    characteristics and components related to alcohol production and fermentation

    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
    +0.32
    2.0%
    191
    +0.07
    0.5%
    503
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.32
    0.40
    67
    +0.07
    0.23
    251
    +0.07
    0.11
    Negative Logits
    ariat
    -0.54
    akeru
    -0.53
    mma
    -0.50
     Nare
    -0.47
    swer
    -0.47
    clave
    -0.47
     Carbuncle
    -0.47
    lde
    -0.46
    ressor
    -0.46
    ernaut
    -0.46
    POSITIVE LOGITS
     considerations
    0.59
     modifiers
    0.52
    speak
    0.51
     interpol
    0.51
     aggregation
    0.51
     levels
    0.50
     modulation
    0.49
     descriptions
    0.48
     speculation
    0.48
     impressions
    0.47
    Activations Density 22.205%

    No Known Activations