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. 13451
    Prev
    Next
    INDEX
    Explanations

    references related to peacekeeping missions, military intervention, and diplomatic efforts for peace

    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
    +0.23
    0.9%
    288
    +0.20
    0.8%
    208
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.23
    0.18
    152
    +0.20
    0.13
    709
    +0.14
    0.10
    Negative Logits
    chy
    -0.87
    advertisement
    -0.82
    GPU
    -0.81
    STDOUT
    -0.79
    ames
    -0.77
    hiba
    -0.74
     Sins
    -0.72
    aches
    -0.72
    åĭ
    -0.71
    PIN
    -0.70
    POSITIVE LOGITS
    keeping
    1.43
    keeper
    1.32
    keepers
    1.29
    ably
    1.17
     treaty
    1.09
    peace
    1.05
     Treaty
    0.99
    abil
    0.99
    ful
    0.98
     treaties
    0.94
    Activations Density 6.544%

    No Known Activations