© 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. 23861
    Prev
    Next
    INDEX
    Explanations

    numerical quantities like statistics or measurements

    oai_token-act-pair · gpt-3.5-turbo

    the word "just" and various numerical representations or references to scoring or statistical performance in sports 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
     disg
    -0.59
    idia
    -0.58
    masters
    -0.52
    catentry
    -0.52
     readily
    -0.51
    idav
    -0.50
    alos
    -0.50
    ymm
    -0.49
    ammers
    -0.49
     xen
    -0.49
    POSITIVE LOGITS
    nine
    1.01
     nine
    0.93
    seven
    0.92
     eight
    0.90
    eight
    0.86
     seven
    0.86
     six
    0.85
    three
    0.83
    five
    0.82
    four
    0.82
    Activations Density 0.140%

    No Known Activations