© 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. 9430
    Prev
    Next
    INDEX
    Explanations

    differences or similarities between different entities

    oai_token-act-pair · gpt-3.5-turbo

    comparisons and contrasts

    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
    ogle
    -0.72
    pletion
    -0.70
    ueller
    -0.69
    umper
    -0.68
    udence
    -0.65
    jury
    -0.65
    raq
    -0.64
    ool
    -0.64
    zy
    -0.64
    efficiency
    -0.64
    POSITIVE LOGITS
     diam
    1.07
     incompatible
    1.04
     kindred
    1.03
     oppos
    1.03
     halves
    0.99
     intertw
    0.99
     insepar
    0.97
     distinct
    0.94
     contrasting
    0.93
     complementary
    0.93
    Activations Density 0.254%

    No Known Activations