© 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. 8-RES-JB
    11. 6278
    Prev
    Next
    INDEX
    Explanations

    dates written in the format of month/day/year

    oai_token-act-pair · gpt-3.5-turbo

    numeric values or timestamps associated with updates or changes

    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
    yang
    -0.73
    auga
    -0.62
    kas
    -0.62
    wang
    -0.61
    iton
    -0.60
    essor
    -0.60
    enza
    -0.60
    err
    -0.59
    gger
    -0.59
    ä¼
    -0.57
    POSITIVE LOGITS
    ths
    1.04
    mber
    0.79
    rm
    0.74
    th
    0.74
     anniversary
    0.71
    actionDate
    0.66
    /,
    0.65
     ceremonies
    0.65
    IME
    0.65
    tenance
    0.64
    Activations Density 0.046%

    No Known Activations