© 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. 12973
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations, organizations, and individuals related to conflict zones and military activities

    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
    566
    +0.10
    0.6%
    299
    +0.08
    0.5%
    608
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.25
    326
    +0.08
    0.25
    659
    +0.08
    0.10
    Negative Logits
    ly
    -0.68
    ndra
    -0.65
    manship
    -0.57
    ewater
    -0.55
    lli
    -0.54
    hire
    -0.53
     Dragonbound
    -0.53
    esville
    -0.52
    neys
    -0.51
     Hercules
    -0.51
    POSITIVE LOGITS
    ĵĺ
    0.57
    istor
    0.56
    uador
    0.55
    ÃĽ
    0.53
    istani
    0.52
    merce
    0.51
    Plot
    0.51
    oglu
    0.50
    ptin
    0.50
    ãĥ³ãĤ¸
    0.49
    Activations Density 10.021%

    No Known Activations