© 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. 11666
    Prev
    Next
    INDEX
    Explanations

    phrases related to text editing and proofreading

    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
    174
    +0.14
    0.4%
    396
    +0.14
    0.4%
    568
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    174
    +0.14
    0.08
    568
    +0.14
    0.07
    288
    +0.13
    0.12
    Negative Logits
     abundantly
    -0.89
    emetery
    -0.88
    ONEY
    -0.84
     Kills
    -0.83
    antz
    -0.82
    RAW
    -0.80
    skill
    -0.79
     Daylight
    -0.79
    inea
    -0.79
    anke
    -0.79
    POSITIVE LOGITS
    tenance
    1.60
    roying
    1.33
    quartered
    1.33
    itored
    1.32
    edIn
    1.14
    ened
    1.14
    ning
    1.13
    ners
    1.12
    osterone
    1.11
    rior
    1.11
    Activations Density 2.321%

    No Known Activations