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. 13445
    Prev
    Next
    INDEX
    Explanations

    phrases related to political and economic expansion

    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
    +0.28
    1.2%
    459
    +0.14
    0.6%
    642
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.28
    0.17
    635
    +0.14
    0.10
    566
    +0.14
    0.10
    Negative Logits
    MET
    -0.83
    ched
    -0.81
    oka
    -0.81
    nee
    -0.78
     ¯
    -0.77
    ches
    -0.76
    ndra
    -0.75
    vana
    -0.75
    âķIJâķIJ
    -0.75
    pee
    -0.74
    POSITIVE LOGITS
    ansion
    0.97
     expansion
    0.97
     expansions
    0.89
     outward
    0.84
    ressive
    0.75
    ivist
    0.75
    sheets
    0.75
    ively
    0.74
     utilization
    0.74
    onential
    0.72
    Activations Density 10.915%

    No Known Activations