© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 6973
    Prev
    Next
    INDEX
    Explanations

    quotations

    oai_token-act-pair · gpt-3.5-turbo

    quoted speech or direct quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prelim
    -0.78
     innov
    -0.72
     adjud
    -0.70
     prec
    -0.70
     tram
    -0.68
     clo
    -0.67
     sho
    -0.66
     encl
    -0.66
     cris
    -0.66
     litter
    -0.66
    POSITIVE LOGITS
    It
    1.13
    We
    1.13
    Certainly
    1.11
    They
    1.08
    Obviously
    1.07
    There
    1.07
    Clearly
    1.06
    I
    1.06
    What
    1.05
    Because
    1.05
    Activations Density 0.133%

    No Known Activations