© 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 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 1142
    Prev
    Next
    INDEX
    Explanations

    references to database / data management terminology and coding (such as ETL, schema, extract, Load, database, tables, rows, columns, data structure, etc.)

    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
    220
    +0.16
    0.6%
    549
    +0.15
    0.6%
    311
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.13
    220
    +0.15
    0.07
    651
    +0.15
    0.08
    Negative Logits
    maid
    -1.01
    igan
    -0.98
    igans
    -0.96
    bah
    -0.92
    iard
    -0.91
    ndra
    -0.85
    acht
    -0.84
    osuke
    -0.83
    ghai
    -0.82
    idding
    -0.82
    POSITIVE LOGITS
    ract
    1.36
    racted
    1.32
    ension
    1.28
    ENDED
    1.26
    ordinary
    1.26
    ensions
    1.26
    ractor
    1.24
    raction
    1.16
    urious
    1.06
    urous
    1.00
    Activations Density 1.410%

    No Known Activations