© 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. 7-RES-JB
    11. 23421
    Prev
    Next
    INDEX
    Explanations

    sentences related to personal experiences or opinions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to emotional states or feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    `.
    -0.70
     ..."
    -0.67
    ".[
    -0.66
     thereto
    -0.64
     ."
    -0.61
    ."[
    -0.60
    ?".
    -0.59
    >]
    -0.59
    ).[
    -0.59
    -->
    -0.59
    POSITIVE LOGITS
     Dunham
    0.74
     Dawkins
    0.70
     Slate
    0.69
     Garfield
    0.67
     Twain
    0.65
     theorist
    0.65
     anecdote
    0.64
     disclaimer
    0.63
     irony
    0.62
     VICE
    0.62
    Activations Density 1.648%

    No Known Activations