© 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. 1-RES-JB
    11. 24262
    Prev
    Next
    INDEX
    Explanations

    words related to the spinal cord and medical procedures/actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to spinal health and retraction issues in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    geist
    -0.99
    igate
    -0.83
    izen
    -0.80
    itect
    -0.73
    igation
    -0.73
    onymous
    -0.73
     tru
    -0.72
     Frey
    -0.71
     Ceres
    -0.71
    ason
    -0.71
    POSITIVE LOGITS
    ornia
    0.86
    ulum
    0.83
     unconditional
    0.82
     cord
    0.79
     spinal
    0.75
    ENTS
    0.72
    redited
    0.69
     amput
    0.69
    poon
    0.68
    thening
    0.68
    Activations Density 0.017%

    No Known Activations