© 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. 8725
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical locations and events

    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
    640
    +0.43
    2.2%
    521
    +0.10
    0.5%
    649
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.43
    0.26
    64
    +0.10
    -0.06
    615
    +0.10
    0.13
    Negative Logits
    otine
    -0.79
    uly
    -0.76
    utics
    -0.71
     wiser
    -0.69
     ideal
    -0.69
     blinded
    -0.69
     estranged
    -0.66
     stimul
    -0.66
     doub
    -0.66
     intended
    -0.65
    POSITIVE LOGITS
    Newsletter
    0.97
    Conclusion
    0.92
    ³³³³³³³³³³³³³³³³
    0.90
    ³³³³³³³³
    0.89
    ³³³³
    0.89
    âĸ¬
    0.85
    KEN
    0.82
    ³³³
    0.82
    ONSORED
    0.82
    ################################
    0.80
    Activations Density 1.062%

    No Known Activations