© 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 EvalsExportsinterp-engineNEWAPI 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. 1121
    Prev
    Next
    INDEX
    Explanations

    causal relationships or alternatives

    oai_token-act-pair · gpt-3.5-turbo

    phrases suggesting alternative outcomes or options

    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
    ocracy
    -0.94
    ETS
    -0.86
     Pony
    -0.83
    ocrats
    -0.79
    ords
    -0.73
     Tycoon
    -0.70
    onday
    -0.69
    erest
    -0.68
    ascus
    -0.67
    eth
    -0.65
    POSITIVE LOGITS
    acles
    1.22
    chard
    1.18
    acle
    1.17
    nam
    1.10
     otherwise
    1.08
    chid
    1.04
     alternatively
    1.03
    ifice
    1.03
    acular
    0.98
     outright
    0.94
    Activations Density 0.137%

    No Known Activations