© 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. 22585
    Prev
    Next
    INDEX
    Explanations

    numerical figures, measurements, and statistics

    oai_token-act-pair · gpt-3.5-turbo

    significant numerical values related to various 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
    Otherwise
    -0.63
     Wouldn
    -0.62
     USSR
    -0.62
     DEFENSE
    -0.60
     Benefits
    -0.59
     would
    -0.58
     wouldn
    -0.57
    Would
    -0.57
     depends
    -0.54
    would
    -0.54
    POSITIVE LOGITS
     lately
    1.35
     recently
    0.91
     recent
    0.85
     now
    0.85
    recent
    0.82
    yet
    0.81
     fue
    0.80
     since
    0.79
     latest
    0.75
    Latest
    0.74
    Activations Density 0.779%

    No Known Activations