© 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. 8-RES-JB
    11. 22706
    Prev
    Next
    INDEX
    Explanations

    keywords related to cancellation or ceasing activities

    oai_token-act-pair · gpt-3.5-turbo

    words related to cancellation events or actions

    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
    rity
    -0.76
    artisan
    -0.76
    nikov
    -0.73
    ocene
    -0.72
    istics
    -0.68
    ixels
    -0.66
    berger
    -0.65
    Redd
    -0.64
    olds
    -0.64
    bour
    -0.63
    POSITIVE LOGITS
     screenings
    0.82
     pregnancies
    0.81
     cancel
    0.80
     cance
    0.80
     cancell
    0.79
     canceled
    0.76
    ulum
    0.75
     vacations
    0.74
     outright
    0.74
    uate
    0.73
    Activations Density 0.029%

    No Known Activations