© 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. 4-RES-JB
    11. 24034
    Prev
    Next
    INDEX
    Explanations

    phrases related to public speaking or giving speeches

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Speaking" as a signal of reported speech or public statements

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

    No Comments

    Negative Logits
    jer
    -0.78
    ét
    -0.74
    76561
    -0.72
    ascade
    -0.70
    aden
    -0.70
    gradation
    -0.70
    \/\/
    -0.68
    abol
    -0.65
    emp
    -0.64
    TAG
    -0.64
    POSITIVE LOGITS
     engagements
    0.89
     aloud
    0.84
    Speaking
    0.74
     volumes
    0.73
     anecd
    0.72
     fluent
    0.71
     spoke
    0.69
     Speaking
    0.68
     Languages
    0.68
    voice
    0.67
    Activations Density 0.017%

    No Known Activations