© 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
    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. 39642
    Prev
    Next
    INDEX
    Explanations

    programming code elements and syntax

    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
    566
    +0.10
    0.6%
    663
    +0.09
    0.5%
    447
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    663
    +0.10
    0.07
    545
    +0.09
    0.07
    502
    +0.09
    0.05
    Negative Logits
    lain
    -0.63
    ij士
    -0.58
     Shooter
    -0.58
     Debor
    -0.57
    EStream
    -0.56
    ãĥ¼ãĥĨ
    -0.56
    milo
    -0.53
     Valkyrie
    -0.52
    cffff
    -0.51
     KP
    -0.50
    POSITIVE LOGITS
    ota
    0.79
    Pad
    0.77
    obi
    0.76
    plom
    0.76
    nex
    0.74
    orno
    0.73
    omi
    0.72
    utenant
    0.71
    ordan
    0.71
    owa
    0.70
    Activations Density 5.029%

    No Known Activations