© 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. 35592
    Prev
    Next
    INDEX
    Explanations

    technical terms and instructions related to technological operations

    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
    +0.31
    1.4%
    551
    +0.16
    0.7%
    326
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.31
    0.40
    447
    +0.16
    0.42
    64
    +0.12
    -0.21
    Negative Logits
     Fighter
    -0.74
     honoring
    -0.70
    raining
    -0.67
     Moz
    -0.66
     Fighting
    -0.65
     hating
    -0.64
     striving
    -0.64
     Quarter
    -0.63
    bred
    -0.63
     BAL
    -0.63
    POSITIVE LOGITS
    't
    1.55
    adian
    1.25
    isters
    1.19
    berra
    1.18
    ister
    1.10
    NOT
    1.08
     easily
    1.03
     attest
    0.98
     afford
    0.98
     be
    0.97
    Activations Density 14.147%

    No Known Activations