© 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. 8711
    Prev
    Next
    INDEX
    Explanations

    words related to technology and contracts

    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
    +0.34
    1.4%
    739
    +0.12
    0.5%
    549
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.34
    0.14
    393
    +0.12
    0.16
    0
    +0.10
    0.13
    Negative Logits
    nces
    -0.90
    bo
    -0.82
    nox
    -0.82
    account
    -0.81
    Deal
    -0.80
     suspic
    -0.80
    é¾įå
    -0.74
    bush
    -0.72
    åĨ
    -0.72
     psychiat
    -0.72
    POSITIVE LOGITS
     vice
    1.02
    rogens
    1.01
     therefore
    1.01
     consequently
    1.00
    rogen
    0.91
     other
    0.87
     others
    0.86
     thus
    0.82
     then
    0.81
    rology
    0.79
    Activations Density 2.585%

    No Known Activations