© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 15365
    Prev
    Next
    INDEX
    Explanations

    phrases indicating something is surprising or unexpected

    oai_token-act-pair · gpt-3.5-turbo

    the concept of surprise associated with certain topics or events

    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
     Accessed
    -0.81
    querque
    -0.79
    stream
    -0.69
    aciously
    -0.68
    interstitial
    -0.67
    bow
    -0.65
    buster
    -0.64
    vance
    -0.64
    omo
    -0.63
    estyles
    -0.63
    POSITIVE LOGITS
     me
    1.30
     outsiders
    1.13
     anyone
    1.04
     us
    1.01
     him
    0.98
     anybody
    0.97
     observers
    0.93
     everyone
    0.93
     insiders
    0.91
     many
    0.87
    Activations Density 0.237%

    No Known Activations