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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 35403
    Prev
    Next
    INDEX
    Explanations

    political statements and commentary

    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
    447
    +0.13
    1.1%
    199
    +0.05
    0.5%
    382
    +0.05
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.13
    0.28
    393
    +0.05
    0.27
    382
    +0.05
    0.10
    Negative Logits
    âĨij
    -0.36
    ratulations
    -0.36
    aries
    -0.35
    achy
    -0.34
    Tes
    -0.34
    ptin
    -0.33
    soDeliveryDate
    -0.32
    iren
    -0.31
    flies
    -0.31
    agar
    -0.31
    POSITIVE LOGITS
     behalf
    0.57
    eness
    0.52
     Wednesday
    0.43
    assis
    0.43
    slaught
    0.41
     Tuesday
    0.40
     Friday
    0.40
    etime
    0.40
     Thursday
    0.39
     Monday
    0.39
    Activations Density 11.565%

    No Known Activations