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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 45111
    Prev
    Next
    INDEX
    Explanations

    references to football, particularly plays and field goals

    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
    314
    +0.13
    0.6%
    140
    +0.10
    0.5%
    526
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.40
    575
    +0.10
    0.28
    651
    +0.10
    0.19
    Negative Logits
     Helpful
    -0.67
     Municip
    -0.61
    TPPStreamerBot
    -0.61
     Supplementary
    -0.60
     Claus
    -0.59
     Firearms
    -0.59
     Parliamentary
    -0.57
     Supplemental
    -0.57
     Converted
    -0.56
     Pharmaceutical
    -0.56
    POSITIVE LOGITS
    ages
    0.96
    ings
    0.96
    code
    0.87
    classes
    0.84
    room
    0.83
    book
    0.82
    bo
    0.80
    brand
    0.79
    busters
    0.79
    bl
    0.79
    Activations Density 16.421%

    No Known Activations