© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 10847
    Prev
    Next
    INDEX
    Explanations

    references to handcuffing people

    oai_token-act-pair · gpt-3.5-turbo

    references to handcuffing and physical restraint

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

    No Comments

    Negative Logits
     Destination
    -0.74
    #$
    -0.68
     Schwarz
    -0.68
     TD
    -0.67
    wagen
    -0.66
     Reasons
    -0.66
    burgh
    -0.65
    oi
    -0.65
    ONSORED
    -0.65
     IST
    -0.64
    POSITIVE LOGITS
     shack
    1.19
     wrists
    0.95
     restraints
    0.95
     handcuffs
    0.94
     ankles
    0.93
     handcuffed
    0.93
     strapped
    0.92
     restrain
    0.88
     leash
    0.87
     chained
    0.87
    Activations Density 0.034%

    No Known Activations