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

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 4401
    Prev
    Next
    INDEX
    Explanations

    mentions of legal or official documents or actions, with specific emphasis on paragraphs or sections labeled with 'Ċ'

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aeda
    -0.70
     ageing
    -0.65
     flats
    -0.63
    sheets
    -0.61
    lihood
    -0.61
     maths
    -0.61
    cius
    -0.61
     volunt
    -0.60
     sustainability
    -0.59
    sterdam
    -0.59
    POSITIVE LOGITS
    SPONSORED
    1.13
    PHOTOS
    1.12
    Scroll
    1.08
    ADVERTISEMENT
    0.82
     Related
    0.78
    Story
    0.78
    Specifically
    0.74
    Bus
    0.71
    î
    0.70
    Eh
    0.69
    Activations Density 0.281%

    No Known Activations