© 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. 18668
    Prev
    Next
    INDEX
    Explanations

    quantitative values or measurements

    oai_token-act-pair · gpt-3.5-turbo

    patterns of evaluation and contrast in narratives

    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
    actionDate
    -0.66
     Babel
    -0.62
     Advice
    -0.61
    ãĤ©
    -0.60
     Photographer
    -0.60
     Canary
    -0.60
    ãĥĺ
    -0.59
     miscon
    -0.58
     Workers
    -0.57
     Lag
    -0.57
    POSITIVE LOGITS
     nevertheless
    0.93
     nonetheless
    0.83
    poons
    0.76
     thrive
    0.75
    este
    0.74
    lean
    0.72
    ISTER
    0.72
    eston
    0.68
     perfectly
    0.65
     thriving
    0.64
    Activations Density 0.816%

    No Known Activations