© 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. 8008
    Prev
    Next
    INDEX
    Explanations

    technical terms related to products, comparisons between different product levels, and descriptions of product features

    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
    288
    +0.17
    0.6%
    183
    +0.17
    0.6%
    746
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.08
    575
    +0.17
    0.06
    651
    +0.15
    0.05
    Negative Logits
    awar
    -1.01
     tremend
    -0.97
     Carth
    -0.87
     Archangel
    -0.86
     Parables
    -0.86
    illac
    -0.84
     mamm
    -0.83
     Nadu
    -0.83
     trust
    -0.81
    ascus
    -0.80
    POSITIVE LOGITS
    prise
    1.42
    prises
    1.23
    tain
    1.18
    prising
    1.18
    tainment
    1.15
    ways
    1.13
    apore
    1.09
    entry
    1.07
    door
    1.07
    TRY
    1.07
    Activations Density 1.093%

    No Known Activations