© 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. 10820
    Prev
    Next
    INDEX
    Explanations

    phrases related to software development and technological progress

    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
    +0.20
    0.8%
    689
    +0.11
    0.4%
    109
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.20
    0.15
    566
    +0.11
    0.12
    689
    +0.11
    0.12
    Negative Logits
     Passenger
    -0.90
     Kev
    -0.83
     Yel
    -0.81
    Bra
    -0.80
    UGH
    -0.79
     Homes
    -0.79
    da
    -0.79
    Jo
    -0.78
     BRA
    -0.77
    CCC
    -0.77
    POSITIVE LOGITS
     contained
    1.24
     relate
    1.17
     occurred
    1.11
     involves
    1.09
     involve
    1.07
     coincided
    1.06
     occur
    1.03
     meant
    1.03
     intersect
    1.01
    atically
    1.01
    Activations Density 3.466%

    No Known Activations