© 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. 8-RES-JB
    11. 24292
    Prev
    Next
    INDEX
    Explanations

    references to a sports team known as the Warriors

    oai_token-act-pair · gpt-3.5-turbo

    references to the Warriors basketball team

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ions
    -1.06
    ories
    -0.89
    ively
    -0.89
    oglobin
    -0.89
    orable
    -0.79
    ioned
    -0.78
    orage
    -0.77
    riad
    -0.76
    icut
    -0.73
    ibly
    -0.72
    POSITIVE LOGITS
    riors
    1.24
    rior
    1.08
    CVE
    0.80
    ¯¯
    0.77
     Oro
    0.75
    fare
    0.73
    ¯¯¯¯
    0.68
    sei
    0.68
    UGH
    0.68
    halla
    0.68
    Activations Density 0.075%

    No Known Activations