© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-RES-JB
    11. 13898
    Prev
    Next
    INDEX
    Explanations

    phrases indicating something is deviating from normal or expected standards

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating something is unusual or not in accordance with expectations

    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
    erity
    -0.76
    ILA
    -0.65
    ilers
    -0.64
    rower
    -0.63
    uania
    -0.62
    aternity
    -0.60
    isel
    -0.59
    Ds
    -0.57
     ALSO
    -0.56
    UMP
    -0.56
    POSITIVE LOGITS
    vable
    0.88
    usable
    0.74
    erous
    0.73
     imagination
    0.73
    acious
    0.71
    whelming
    0.70
    sighted
    0.68
     scope
    0.67
    fortable
    0.67
     ballpark
    0.66
    Activations Density 0.222%

    No Known Activations