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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 9973
    Prev
    Next
    INDEX
    Explanations

    mentions of numbers that indicate quantities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific products and their associations with actions or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FTA
    -1.00
     Tend
    -0.99
     DF
    -0.96
     TF
    -0.93
     Ft
    -0.89
     Fir
    -0.88
     Deer
    -0.86
     Fib
    -0.86
     Fet
    -0.85
     Dent
    -0.85
    POSITIVE LOGITS
    arn
    0.98
    ogen
    0.96
    ogie
    0.92
    ocker
    0.90
    ocratic
    0.89
    ococ
    0.87
     Loch
    0.86
    og
    0.84
    OC
    0.81
    ika
    0.81
    Activations Density 0.558%

    No Known Activations