© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 2209
    Prev
    Next
    INDEX
    Explanations

    words related to habitual behaviors or established patterns

    oai_token-act-pair · gpt-3.5-turbo

    terms related to patterns of behavior and responsibilities

    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
    tics
    -0.71
    sites
    -0.71
     finances
    -0.68
     wards
    -0.67
    results
    -0.67
    tops
    -0.66
    drops
    -0.65
    features
    -0.65
    anders
    -0.65
    anes
    -0.65
    POSITIVE LOGITS
    atical
    0.97
     similar
    0.92
     analogous
    0.89
     akin
    0.88
     reminiscent
    0.87
     whereby
    0.87
    less
    0.86
     resembling
    0.78
    like
    0.72
    icum
    0.72
    Activations Density 0.331%

    No Known Activations