© 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. 9-RES-JB
    11. 15428
    Prev
    Next
    INDEX
    Explanations

    phrases indicating belief or confidence in being able to accomplish something

    oai_token-act-pair · gpt-3.5-turbo

    expressions of capability or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    furt
    -0.90
     Cheong
    -0.75
    teen
    -0.68
    quartered
    -0.66
    pend
    -0.62
    Loading
    -0.62
    76561
    -0.61
     Falling
    -0.61
    spection
    -0.61
    checking
    -0.60
    POSITIVE LOGITS
     afford
    1.23
    't
    1.14
     safely
    1.05
     withstand
    0.99
     achieve
    0.97
     manage
    0.97
     tolerate
    0.95
     handle
    0.95
     improve
    0.94
     cope
    0.94
    Activations Density 0.191%

    No Known Activations