© 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. 11-RES-JB
    11. 22588
    Prev
    Next
    INDEX
    Explanations

    contractions where the apostrophe is missing or replaced by unusual characters

    oai_token-act-pair · gpt-3.5-turbo

    instances of negation or expressions of inability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     commons
    -0.70
     heroin
    -0.69
     kicker
    -0.68
     polio
    -0.67
     pyramid
    -0.66
     Robin
    -0.65
     black
    -0.64
     Lob
    -0.63
     Wilmington
    -0.63
     Taliban
    -0.62
    POSITIVE LOGITS
    ï¸ı
    1.18
    ¯¯
    1.04
    Ì
    1.01
    âĻ
    1.01
    iversary
    1.01
    ̶
    1.00
    âĪ
    0.95
    âĢ
    0.94
    âĶĢâĶĢâĶĢâĶĢ
    0.94
    âĶĢ
    0.94
    Activations Density 0.180%

    No Known Activations