© 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. 32245
    Prev
    Next
    INDEX
    Explanations

    patterns related to coding or special characters

    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
    195
    +0.09
    0.5%
    538
    +0.09
    0.5%
    508
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.09
    0.10
    373
    +0.09
    -0.16
    393
    +0.08
    0.20
    Negative Logits
    theless
    -0.98
    anwhile
    -0.77
    terday
    -0.66
    apon
    -0.65
    abwe
    -0.64
    staking
    -0.64
     destro
    -0.64
    ovsky
    -0.61
    ascus
    -0.60
    iversary
    -0.59
    POSITIVE LOGITS
    AppData
    0.79
    wcsstore
    0.62
    ³
    0.61
     Firefly
    0.59
    µ
    0.55
    ¯
    0.53
    ©¶æ¥µ
    0.53
     æľ
    0.52
    ł
    0.52
    Ĵ
    0.52
    Activations Density 6.458%

    No Known Activations