© 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. 6-RES-JB
    11. 17411
    Prev
    Next
    INDEX
    Explanations

    phrases related to being restricted or tied up physically or figuratively

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "tied up" or similar expressions indicating restraint or confinement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     catalyst
    -0.65
     gearing
    -0.64
    Maker
    -0.63
     sensitivity
    -0.63
    bits
    -0.62
    ceivable
    -0.59
     cast
    -0.59
    oly
    -0.57
     pierced
    -0.56
    grim
    -0.55
    POSITIVE LOGITS
    river
    0.91
    rights
    0.83
    stock
    0.76
    bage
    0.73
    irts
    0.71
    tics
    0.70
    skirts
    0.69
    icts
    0.68
    dates
    0.68
    rats
    0.67
    Activations Density 0.048%

    No Known Activations