© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 7152
    Prev
    Next
    INDEX
    Explanations

    content related to sports

    oai_token-act-pair · gpt-3.5-turbo

    references to participation or membership in teams or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    witch
    -0.80
    abel
    -0.75
    rand
    -0.73
    mith
    -0.69
    aeus
    -0.69
    verb
    -0.67
    utm
    -0.67
    amac
    -0.66
    teness
    -0.65
    ´
    -0.65
    POSITIVE LOGITS
     fray
    1.41
     fold
    1.25
     ranks
    1.24
     workforce
    1.10
     forefront
    1.10
     confines
    1.06
     throne
    0.93
     midst
    0.93
     prestigious
    0.91
     spotlight
    0.90
    Activations Density 0.218%

    No Known Activations