© 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. 24091
    Prev
    Next
    INDEX
    Explanations

    words surrounded by specific characters (such as 'Ċ') on both sides

    oai_token-act-pair · gpt-3.5-turbo

    the end of sections or documents

    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
     occas
    -0.92
     neighb
    -0.77
     citiz
    -0.77
     unprepared
    -0.76
     undermin
    -0.75
     inactive
    -0.73
     diving
    -0.71
     representation
    -0.71
     aging
    -0.70
     underest
    -0.70
    POSITIVE LOGITS
    ³³³³
    1.33
    ³³³³³³³³
    1.32
    ³³³³³³³³³³³³³³³³
    1.31
    ³³³
    1.28
    posted
    1.13
    Posted
    1.09
    Tonight
    1.09
    ³³
    1.08
    Palestinian
    1.06
    Anonymous
    1.04
    Activations Density 0.146%

    No Known Activations