© 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. 17221
    Prev
    Next
    INDEX
    Explanations

    instances of the word "were" followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases that imply hypothetical situations

    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
    abre
    -0.73
     +++
    -0.68
    Ñģ
    -0.67
    Products
    -0.65
     Quarterly
    -0.64
     ¶
    -0.63
    âĿ
    -0.60
    oria
    -0.59
     Documentation
    -0.59
     fascination
    -0.58
    POSITIVE LOGITS
     hypot
    0.88
    wolves
    0.88
     somehow
    0.73
     ever
    0.71
     truly
    0.71
     betting
    0.67
    webkit
    0.65
     Rowling
    0.64
     solely
    0.62
    canon
    0.62
    Activations Density 0.082%

    No Known Activations