© 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 Local
    5. 6-RES_SCL-AJT
    6. 40788
    Prev
    Next
    INDEX
    Explanations

    facts and details related to military activities and events

    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
    468
    +0.08
    0.5%
    383
    +0.08
    0.4%
    373
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.08
    -0.11
    699
    +0.08
    0.03
    598
    +0.08
    0.04
    Negative Logits
    xual
    -0.60
    kel
    -0.55
     Halls
    -0.55
    nels
    -0.53
    paces
    -0.52
     Esp
    -0.50
     Faul
    -0.47
    uador
    -0.47
    ãĤ¼ãĤ¦ãĤ¹
    -0.47
    sein
    -0.47
    POSITIVE LOGITS
    oths
    0.94
    othes
    0.81
    oner
    0.80
    apy
    0.80
    othe
    0.78
    bered
    0.73
    zin
    0.70
    oth
    0.68
     far
    0.65
    aps
    0.65
    Activations Density 4.152%

    No Known Activations