© 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. 17837
    Prev
    Next
    INDEX
    Explanations

    phrases indicating surprise or a twist in an expected narrative

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating realizations or conclusions about various topics

    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
    resh
    -0.77
    ropolitan
    -0.73
    lain
    -0.71
     Colleg
    -0.67
    è¦ļéĨĴ
    -0.66
    atana
    -0.65
    negie
    -0.64
    ities
    -0.63
    itation
    -0.63
     Zan
    -0.61
    POSITIVE LOGITS
     sour
    0.72
     beet
    0.69
    ĸ
    0.68
    Ī
    0.66
    terday
    0.63
     hormones
    0.63
     burgers
    0.63
     tides
    0.62
    \\\\\\\\\\\\\\\\
    0.62
    CVE
    0.61
    Activations Density 0.022%

    No Known Activations