© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 34742
    Prev
    Next
    INDEX
    Explanations

    words related to military strategy and technology

    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
    +0.38
    2.0%
    665
    +0.09
    0.5%
    82
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    375
    +0.38
    0.11
    665
    +0.09
    0.24
    70
    +0.09
    0.19
    Negative Logits
    mas
    -0.61
    con
    -0.61
    beat
    -0.59
    agar
    -0.59
    fur
    -0.57
    hon
    -0.57
    com
    -0.55
    Press
    -0.55
    Inv
    -0.54
    aff
    -0.54
    POSITIVE LOGITS
     theirs
    0.74
     something
    0.66
     another
    0.64
     lots
    0.64
     hers
    0.63
     them
    0.62
     multiple
    0.59
     him
    0.59
     THEM
    0.58
     anything
    0.58
    Activations Density 21.392%

    No Known Activations