© 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. 11271
    Prev
    Next
    INDEX
    Explanations

    instances of the word "survey"

    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
    508
    +0.13
    0.6%
    163
    +0.13
    0.5%
    235
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    235
    +0.13
    0.06
    744
    +0.13
    0.06
    195
    +0.12
    0.01
    Negative Logits
     Nanto
    -0.99
     marrow
    -0.80
    itsch
    -0.76
    tsky
    -0.75
    burning
    -0.72
    lore
    -0.72
     soluble
    -0.71
    practice
    -0.70
    ife
    -0.70
     affili
    -0.68
    POSITIVE LOGITS
     questions
    1.10
     inquired
    1.08
     inquire
    1.06
     respondents
    1.06
     quer
    1.05
    naire
    1.04
     respondent
    1.02
     rhet
    1.01
     Questions
    1.00
     survey
    0.99
    Activations Density 1.574%

    No Known Activations