© 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. 15668
    Prev
    Next
    INDEX
    Explanations

    instances of expressing surprise about something being observed for the first time

    oai_token-act-pair · gpt-3.5-turbo

    expressions of novelty or unique experiences

    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
    •layer 7 - surprise

    No Comments

    Negative Logits
    externalActionCode
    -0.68
    ials
    -0.66
    recy
    -0.61
    ayers
    -0.59
    Shape
    -0.58
    bi
    -0.56
    Charge
    -0.56
    roup
    -0.55
    uli
    -0.55
     refin
    -0.55
    POSITIVE LOGITS
     anything
    0.93
     anybody
    0.92
     anyone
    0.84
    anything
    0.77
     anywhere
    0.76
     dime
    0.74
     ANY
    0.74
     nor
    0.69
     bothered
    0.68
     any
    0.67
    Activations Density 0.069%

    No Known Activations