© 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. 8134
    Prev
    Next
    INDEX
    Explanations

    pronouns 'it' or 'it's a'

    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
    393
    +0.32
    1.1%
    566
    +0.18
    0.6%
    515
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.32
    0.09
    252
    +0.18
    0.09
    259
    +0.15
    0.08
    Negative Logits
    hips
    -0.92
    idth
    -0.91
    cox
    -0.88
     installments
    -0.82
    ãĤ¹ãĥĪ
    -0.81
    ength
    -0.81
    ohyd
    -0.81
    izations
    -0.80
     Credits
    -0.80
    iege
    -0.78
    POSITIVE LOGITS
    self
    1.39
    chy
    1.38
    unes
    1.30
    iner
    1.19
    ueller
    1.15
    alian
    1.13
    fits
    1.07
     beh
    1.07
    zik
    1.05
     pains
    1.04
    Activations Density 0.840%

    No Known Activations