© 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. 16763
    Prev
    Next
    INDEX
    Explanations

    verbs indicating permission or ability

    oai_token-act-pair · gpt-3.5-turbo

    actions related to living, moving, and participating in activities or events

    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
    æľ
    -0.73
    ãĥ¼ãĥĨãĤ£
    -0.68
    ãĤ·ãĥ£
    -0.64
    é¾įå¥ij士
    -0.62
    ãĥĨ
    -0.62
    ãĥĻ
    -0.61
    èĪ
    -0.61
    ãĥ¬
    -0.60
    Org
    -0.60
    æ©Ł
    -0.60
    POSITIVE LOGITS
     freely
    1.24
     safely
    1.05
     comfortably
    1.01
     indefinitely
    0.93
     efficiently
    0.91
     uninterrupted
    0.88
     easily
    0.87
     confidently
    0.86
     effectively
    0.83
     unim
    0.82
    Activations Density 0.428%

    No Known Activations