© 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. 9-RES-JB
    11. 4304
    Prev
    Next
    INDEX
    Explanations

    words related to actions of stopping, canceling, or terminating something

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sov
    -0.83
    hene
    -0.82
    aceae
    -0.76
    ebus
    -0.73
    rigan
    -0.70
    Lenin
    -0.70
    idable
    -0.70
    wm
    -0.69
    eh
    -0.69
    inos
    -0.69
    POSITIVE LOGITS
     offending
    0.86
     refunds
    0.81
     recommending
    0.80
     indefinitely
    0.78
     its
    0.77
     unnecessary
    0.77
     plans
    0.77
     registrations
    0.74
     altogether
    0.74
     advertising
    0.73
    Activations Density 0.213%

    No Known Activations