© 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. 15675
    Prev
    Next
    INDEX
    Explanations

    comparisons asking to choose between options

    oai_token-act-pair · gpt-3.5-turbo

    references to choices or options in various contexts

    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
    ļéĨĴ
    -0.87
    enture
    -0.78
    limited
    -0.72
    ²¾
    -0.69
    zek
    -0.68
    isse
    -0.67
    GGGGGGGG
    -0.65
    paren
    -0.64
    livious
    -0.64
    ©¶æ¥µ
    -0.62
    POSITIVE LOGITS
     suits
    1.10
     best
    1.04
     dominates
    1.01
     corresponds
    1.00
     wins
    0.95
     fits
    0.95
     BEST
    0.92
     deserves
    0.89
     tops
    0.87
     inspires
    0.85
    Activations Density 0.176%

    No Known Activations