© 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. 3566
    Prev
    Next
    INDEX
    Explanations

    phrases indicating an expected outcome or result

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing surprise or lack of surprise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ouf
    -0.77
    tein
    -0.68
    swick
    -0.61
    neys
    -0.61
    cles
    -0.59
     avenues
    -0.59
     promot
    -0.59
    %]
    -0.58
     LINK
    -0.58
     pursuits
    -0.57
    POSITIVE LOGITS
     surprise
    1.34
     shock
    1.12
    shock
    0.97
     unsur
    0.89
     relief
    0.88
     Surprise
    0.87
     surprising
    0.84
     surprises
    0.83
     no
    0.81
     revelation
    0.78
    Activations Density 0.068%

    No Known Activations