© 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. 7363
    Prev
    Next
    INDEX
    Explanations

    common verb suffixes, such as "-ed" and "-ing," as well as some specific names

    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
    420
    +0.19
    0.6%
    326
    +0.18
    0.6%
    97
    +0.18
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.19
    0.07
    659
    +0.18
    0.06
    190
    +0.18
    0.05
    Negative Logits
     Palestin
    -1.09
    anamo
    -1.08
     ILCS
    -1.07
    ohydrate
    -1.04
     Adin
    -1.02
     tremend
    -1.01
    ourcing
    -1.01
    ensical
    -1.00
    ashtra
    -1.00
    ancial
    -1.00
    POSITIVE LOGITS
    llers
    1.84
    ller
    1.65
    ptic
    1.60
    rette
    1.56
    lling
    1.49
    jriwal
    1.45
    vich
    1.41
    ying
    1.39
    lev
    1.32
    ls
    1.31
    Activations Density 1.377%

    No Known Activations