© 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. 7156
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the status, progress, or caution related to ongoing projects or processes

    oai_token-act-pair · gpt-3.5-turbo
    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
    illet
    -0.61
    riot
    -0.56
    IVERS
    -0.56
    ukong
    -0.55
     Benefits
    -0.55
     TWO
    -0.54
    adelphia
    -0.54
     spons
    -0.53
     HELL
    -0.53
     murd
    -0.53
    POSITIVE LOGITS
     unsure
    0.94
     cautioned
    0.92
     unclear
    0.92
     uncertain
    0.89
     unlikely
    0.88
     uncertainties
    0.87
     caution
    0.86
     speculative
    0.86
     remains
    0.85
     caveats
    0.85
    Activations Density 0.544%

    No Known Activations