© 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. 36268
    Prev
    Next
    INDEX
    Explanations

    specific patterns or sequences of characters within longer texts

    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
    +0.23
    1.2%
    314
    +0.14
    0.7%
    637
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.23
    -0.04
    293
    +0.14
    0.12
    52
    +0.10
    0.09
    Negative Logits
     Leilan
    -0.65
     KS
    -0.61
     KP
    -0.59
     Cot
    -0.58
     KL
    -0.58
     Oriental
    -0.58
     Watkins
    -0.57
     Gaul
    -0.57
     Kau
    -0.57
     Kern
    -0.56
    POSITIVE LOGITS
    vernment
    0.97
    theless
    0.85
    actly
    0.85
    ancial
    0.83
    ploy
    0.81
    terday
    0.77
    undred
    0.77
    usterity
    0.77
    ̶
    0.75
    oyal
    0.75
    Activations Density 12.207%

    No Known Activations