© 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. 8-RES-JB
    11. 7036
    Prev
    Next
    INDEX
    Explanations

    government-related terms and names of government entities

    oai_token-act-pair · gpt-3.5-turbo

    references to legal or governmental offices, particularly those of attorneys

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VERT
    -0.73
    onyms
    -0.69
    TEXTURE
    -0.68
     swaps
    -0.67
     dots
    -0.66
     travellers
    -0.65
    Js
    -0.65
    yz
    -0.64
    Brit
    -0.63
    Pure
    -0.62
    POSITIVE LOGITS
     office
    1.13
    hip
    1.07
    office
    1.03
     Office
    1.01
    leeve
    0.90
     offices
    0.90
    hips
    0.87
    orship
    0.85
    ullivan
    0.82
    alty
    0.81
    Activations Density 0.134%

    No Known Activations