© 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. 6-RES-JB
    11. 18485
    Prev
    Next
    INDEX
    Explanations

    keywords related to calls to action, instructions, or directives

    oai_token-act-pair · gpt-3.5-turbo

    calls to action or prompts related to obtaining information or following updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    minist
    -0.73
    )",
    -0.71
     ().
    -0.60
     respectively
    -0.60
     session
    -0.60
     laying
    -0.60
     UD
    -0.58
     maturity
    -0.58
     swe
    -0.57
    ,,,,
    -0.57
    POSITIVE LOGITS
    Alert
    0.89
     Continued
    0.88
     SHARES
    0.85
     WATCHED
    0.85
    Featured
    0.84
    Correction
    0.84
     Expand
    0.83
     Slate
    0.83
     Email
    0.82
    Follow
    0.82
    Activations Density 0.178%

    No Known Activations