© 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. 6968
    Prev
    Next
    INDEX
    Explanations

    texts indicating Python exceptions being thrown

    oai_token-act-pair · gpt-3.5-turbo

    instances of high-scoring plays or performances in sports contexts

    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
     occas
    -0.80
     endeav
    -0.78
     proport
    -0.78
     tremend
    -0.77
     disillusion
    -0.70
     exha
    -0.69
     imperson
    -0.69
     footing
    -0.69
     underest
    -0.68
     experien
    -0.67
    POSITIVE LOGITS
    Posted
    1.51
    posted
    1.26
    ³³³³³³³³³³³³³³³³
    1.10
    ³³³³³³³³
    1.04
    Article
    1.03
    ³³³³
    1.02
    Anyway
    1.02
    UPDATE
    0.99
    Update
    0.99
    Anonymous
    0.97
    Activations Density 0.519%

    No Known Activations