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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 40815
    Prev
    Next
    INDEX
    Explanations

    mentions of governmental bodies, political events, and international relations

    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
    488
    +0.09
    0.5%
    86
    +0.07
    0.4%
    353
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.09
    0.16
    482
    +0.07
    0.06
    188
    +0.07
    0.09
    Negative Logits
    ighth
    -0.66
    lectic
    -0.62
    xes
    -0.58
    ¾
    -0.57
    quit
    -0.56
    ¥µ
    -0.55
     Twain
    -0.54
    agin
    -0.54
    kson
    -0.54
    uts
    -0.53
    POSITIVE LOGITS
     opposition
    0.60
     Mub
    0.60
     democracy
    0.53
     uprising
    0.52
     movement
    0.52
     coffers
    0.52
     committee
    0.52
     liberties
    0.52
     watchdog
    0.51
     republic
    0.49
    Activations Density 7.925%

    No Known Activations