© 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. 15296
    Prev
    Next
    INDEX
    Explanations

    brands and products along with associated actions or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly semicolons

    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
    ront
    -0.80
    senal
    -0.78
    rio
    -0.75
    din
    -0.74
    odes
    -0.73
    ric
    -0.72
    omorphic
    -0.71
    orts
    -0.70
    formation
    -0.70
    iji
    -0.69
    POSITIVE LOGITS
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.95
     alternatively
    0.95
     thence
    0.95
     furthermore
    0.90
     moreover
    0.82
    -)
    0.80
     Flavoring
    0.79
     };
    0.78
     consequently
    0.77
     additionally
    0.77
    Activations Density 0.042%

    No Known Activations