© 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. 11218
    Prev
    Next
    INDEX
    Explanations

    words ending in '-ed' or '-ing'

    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
    688
    +0.14
    0.5%
    746
    +0.13
    0.4%
    616
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    747
    +0.14
    0.03
    111
    +0.13
    0.04
    268
    +0.13
    0.03
    Negative Logits
    ĸļ
    -1.08
     Canaver
    -1.02
     Loren
    -0.96
    soDeliveryDate
    -0.91
    isSpecialOrderable
    -0.88
     mouths
    -0.87
    anson
    -0.86
    CN
    -0.86
    quickShipAvailable
    -0.85
    retty
    -0.85
    POSITIVE LOGITS
    iations
    1.30
    iation
    1.27
    iate
    1.17
    rations
    1.12
    iates
    1.10
    inished
    1.07
    Grade
    1.04
    Applic
    1.03
    iated
    1.02
    isites
    0.97
    Activations Density 0.817%

    No Known Activations