© 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. 11429
    Prev
    Next
    INDEX
    Explanations

    code snippets related to programming in languages like Java or Python

    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
    48
    +0.15
    0.5%
    524
    +0.13
    0.4%
    59
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.15
    0.05
    160
    +0.13
    0.06
    6
    +0.12
    0.06
    Negative Logits
     TAMADRA
    -1.00
     Vaugh
    -0.93
     leveled
    -0.91
     Jou
    -0.90
     Siren
    -0.89
     ende
    -0.89
     merciless
    -0.87
     Oo
    -0.87
     injected
    -0.87
     vind
    -0.87
    POSITIVE LOGITS
    local
    1.31
    feature
    1.24
    sid
    1.24
    hello
    1.24
    gt
    1.21
    gall
    1.19
    example
    1.19
    hs
    1.18
    foo
    1.17
    tri
    1.16
    Activations Density 0.544%

    No Known Activations