© 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. 10631
    Prev
    Next
    INDEX
    Explanations

    sequenced events, particularly related to actions or accomplishments

    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
    +0.31
    1.0%
    718
    +0.15
    0.5%
    703
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.31
    0.13
    393
    +0.15
    0.14
    0
    +0.14
    0.12
    Negative Logits
    DX
    -1.06
    CRIP
    -1.06
    ULTS
    -1.01
    Tes
    -0.99
    ÃĽ
    -0.98
    Magikarp
    -0.97
    dayName
    -0.97
    MT
    -0.97
    ADVERTISEMENT
    -0.96
    CLA
    -0.95
    POSITIVE LOGITS
    rogen
    1.64
     therefore
    1.53
     consequently
    1.51
     thus
    1.39
     hence
    1.39
    rogens
    1.35
     thereby
    1.31
     foremost
    1.31
     possibly
    1.30
     hopefully
    1.24
    Activations Density 1.756%

    No Known Activations