© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3128
    Prev
    Next
    INDEX
    Explanations

    phrases that express surprise or emphasis, often beginning with 'Oh' and 'And'

    oai_token-act-pair · gpt-3.5-turbo
    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
    BILITIES
    -0.89
    Ö¼
    -0.81
    actionDate
    -0.74
    orea
    -0.73
    alion
    -0.72
    ograp
    -0.71
    arov
    -0.71
    acters
    -0.70
    cius
    -0.69
    arlane
    -0.68
    POSITIVE LOGITS
     dear
    0.79
     gasp
    0.71
     blasphemy
    0.69
     heavens
    0.66
     yea
    0.66
     shudder
    0.63
     yes
    0.63
     horror
    0.62
     Miss
    0.61
     hurry
    0.61
    Activations Density 0.054%

    No Known Activations