© 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. 612
    Prev
    Next
    INDEX
    Explanations

    mentions and descriptions related to specific people or individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals in images or photographs

    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
    ixon
    -0.74
    ãĤ¦ãĤ¹
    -0.66
     inquiries
    -0.65
    Questions
    -0.64
    Information
    -0.64
    uries
    -0.64
    izons
    -0.63
    encies
    -0.63
    ollah
    -0.61
    ĨĴ
    -0.61
    POSITIVE LOGITS
     smiling
    1.55
     grinning
    1.47
     wearing
    1.46
     kneeling
    1.40
     posing
    1.38
     interacting
    1.37
     gazing
    1.37
     dancing
    1.36
     hugging
    1.36
     walking
    1.35
    Activations Density 0.500%

    No Known Activations