© 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. 6235
    Prev
    Next
    INDEX
    Explanations

    verbs related to repeating or doing something over and over

    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
    195
    +0.15
    0.5%
    727
    +0.15
    0.5%
    269
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    195
    +0.15
    0.02
    710
    +0.15
    0.05
    725
    +0.15
    0.04
    Negative Logits
    uana
    -1.21
    sie
    -1.17
    isu
    -1.13
    tesy
    -1.12
    istical
    -1.06
    oak
    -1.04
    icial
    -1.02
    animous
    -1.02
    chens
    -1.01
    insula
    -1.00
    POSITIVE LOGITS
     repeat
    1.17
    lly
    1.17
    nces
    1.16
     repeats
    1.12
     repeating
    1.10
     digits
    1.09
    ability
    1.09
     playthrough
    1.09
     offenders
    1.07
    repeat
    1.02
    Activations Density 0.990%

    No Known Activations