© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 14354
    Prev
    Next
    INDEX
    Explanations

    technical terms related to military operations or equipment

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    70
    +0.15
    0.5%
    640
    +0.15
    0.5%
    393
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    517
    +0.15
    0.07
    739
    +0.15
    0.04
    160
    +0.14
    0.10
    Negative Logits
    ieth
    -0.96
     Rica
    -0.96
     timely
    -0.90
    oppable
    -0.90
    cember
    -0.90
     Simulator
    -0.90
    reau
    -0.88
    ottesville
    -0.87
    enhagen
    -0.85
     avail
    -0.84
    POSITIVE LOGITS
    sic
    1.73
    literally
    1.63
    meaning
    1.57
    Greek
    1.32
    translation
    1.28
    aka
    1.26
     meaning
    1.24
     aka
    1.11
    É
    1.04
    rough
    1.03
    Activations Density 2.241%

    No Known Activations