© 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. 10-RES-JB
    11. 22120
    Prev
    Next
    INDEX
    Explanations

    legal and procedural terms

    oai_token-act-pair · gpt-3.5-turbo

    action verbs related to legal or regulatory contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nightmares
    -0.87
     boredom
    -0.85
     glimps
    -0.84
     glances
    -0.77
     chatter
    -0.76
     headaches
    -0.76
     moments
    -0.76
     itch
    -0.76
     everyday
    -0.75
    aceae
    -0.75
    POSITIVE LOGITS
    register
    1.06
    cluded
    1.03
    clude
    1.01
    license
    1.01
    authorized
    0.99
    ceed
    0.99
    wrote
    0.97
    igned
    0.96
    ondon
    0.94
    activate
    0.93
    Activations Density 0.111%

    No Known Activations