© 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. 7271
    Prev
    Next
    INDEX
    Explanations

    adjectives or verbs related to uncertainties or errors

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to risks and mistakes in decision-making

    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
    trak
    -0.78
    OV
    -0.73
    atorium
    -0.71
    leasing
    -0.70
    ACP
    -0.68
    Rush
    -0.66
    asus
    -0.66
    owder
    -0.65
     VID
    -0.65
    ramid
    -0.65
    POSITIVE LOGITS
    omething
    1.05
     gal
    1.04
    pace
    1.02
    poons
    0.99
    heet
    0.98
    paces
    0.96
    cale
    0.96
    ensical
    0.95
    mith
    0.93
    creen
    0.92
    Activations Density 0.382%

    No Known Activations