© 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. 10-RES-JB
    11. 2232
    Prev
    Next
    INDEX
    Explanations

    references to notable figures or entities in specific contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to artistic works or events

    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
     (>
    -0.95
     (<
    -0.86
    sbm
    -0.86
     UNCLASSIFIED
    -0.83
    nor
    -0.78
    soever
    -0.73
    ascript
    -0.72
    lees
    -0.72
     (âĪĴ
    -0.71
    20439
    -0.71
    POSITIVE LOGITS
     downright
    0.91
     prank
    0.90
     revenge
    0.86
     somet
    0.84
     kicker
    0.79
     awfully
    0.78
     trick
    0.77
     booze
    0.77
     adorable
    0.77
     naughty
    0.75
    Activations Density 0.903%

    No Known Activations