© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 7569
    Prev
    Next
    INDEX
    Explanations

    instructions or steps sequences related to technology or software

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    124
    +0.12
    0.5%
    332
    +0.12
    0.5%
    615
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    331
    +0.12
    0.05
    412
    +0.12
    0.05
    353
    +0.11
    0.04
    Negative Logits
    enegger
    -0.96
    comfort
    -0.88
    Wil
    -0.86
    ilan
    -0.84
    avier
    -0.81
    hower
    -0.78
    Marcus
    -0.78
    atchewan
    -0.76
    Texture
    -0.74
    Luc
    -0.73
    POSITIVE LOGITS
    exist
    0.83
     shine
    0.81
     differ
    0.77
    ?)
    0.74
     flourish
    0.74
     Pry
    0.71
     trickle
    0.70
     faire
    0.70
    andom
    0.70
     prophes
    0.68
    Activations Density 1.834%

    No Known Activations