© 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. 7974
    Prev
    Next
    INDEX
    Explanations

    phrases related to product features or specifications

    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
    238
    +0.35
    1.1%
    643
    +0.18
    0.6%
    385
    +0.17
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    238
    +0.35
    0.09
    643
    +0.18
    0.04
    326
    +0.17
    0.07
    Negative Logits
    YC
    -1.19
    erker
    -1.14
    ership
    -1.01
     untreated
    -0.99
    ļé
    -0.99
     Vinyl
    -0.99
    ĸļ
    -0.97
    Ĥ¬
    -0.96
     Takeru
    -0.94
     Parad
    -0.93
    POSITIVE LOGITS
    vana
    1.98
    ror
    1.59
    rha
    1.57
    mingham
    1.52
    bid
    1.50
    lessly
    1.43
    cles
    1.41
    rr
    1.35
    andom
    1.35
    ilateral
    1.33
    Activations Density 1.490%

    No Known Activations