© 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. 35056
    Prev
    Next
    INDEX
    Explanations

    names related to individuals

    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
    554
    +0.13
    0.5%
    149
    +0.12
    0.5%
    288
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    442
    +0.13
    0.12
    649
    +0.12
    0.05
    301
    +0.12
    0.08
    Negative Logits
    boards
    -0.91
    board
    -0.89
    words
    -0.87
    flame
    -0.83
    BOOK
    -0.82
    DonaldTrump
    -0.74
    chal
    -0.71
     PAGE
    -0.71
    ACP
    -0.71
    fty
    -0.70
    POSITIVE LOGITS
    undy
    1.38
    urg
    1.21
    lar
    1.20
    atory
    1.18
    itating
    1.13
    sburgh
    1.08
    itated
    1.04
    nut
    1.03
    itation
    1.02
    nant
    1.02
    Activations Density 9.068%

    No Known Activations