© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 21615
    Prev
    Next
    INDEX
    Explanations

    references to the main story in a publication or article

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "main" or central themes within the text

    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
    Not in Any Lists

    No Comments

    Negative Logits
    aimon
    -0.73
     Lauder
    -0.68
     Benefit
    -0.66
     Centauri
    -0.66
     Comet
    -0.64
    »Ĵ
    -0.64
    ledged
    -0.62
     Emin
    -0.62
    naires
    -0.59
     Nationwide
    -0.58
    POSITIVE LOGITS
    stay
    0.94
     story
    0.82
    tenance
    0.74
    theme
    0.73
    deck
    0.72
     source
    0.71
     theme
    0.71
    story
    0.70
    inion
    0.67
    gallery
    0.65
    Activations Density 0.009%

    No Known Activations