© 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. 7-RES-JB
    11. 20600
    Prev
    Next
    INDEX
    Explanations

    dates and months in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to specific months and years mentioned in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    goo
    -0.68
    EStreamFrame
    -0.66
    Condition
    -0.64
    onite
    -0.62
    Done
    -0.62
    vec
    -0.62
    artifacts
    -0.60
    debian
    -0.59
    ococ
    -0.59
    ssl
    -0.58
    POSITIVE LOGITS
     meanwhile
    0.83
     however
    0.74
    ruary
    0.72
    ileaks
    0.68
     Suzuki
    0.66
     Newsweek
    0.65
     Accessed
    0.64
    ccording
    0.64
     Wikileaks
    0.63
    ledge
    0.61
    Activations Density 0.178%

    No Known Activations