© 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. 1265
    Prev
    Next
    INDEX
    Explanations

    patterns related to self-inflicted actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to self-inflicted conditions or actions

    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
    KEY
    -0.70
     stakes
    -0.69
    DAY
    -0.66
     mercury
    -0.66
     AMERICA
    -0.65
    ãĥīãĥ©ãĤ´ãĥ³
    -0.65
     Collider
    -0.64
    sea
    -0.63
     Spectre
    -0.62
     belts
    -0.61
    POSITIVE LOGITS
    essed
    0.90
    itled
    0.82
    ointed
    0.79
    licted
    0.75
    oming
    0.74
    tenance
    0.73
    structed
    0.72
    rimination
    0.72
    ceived
    0.70
    destruct
    0.70
    Activations Density 0.039%

    No Known Activations