© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7788
    Prev
    Next
    INDEX
    Explanations

    numerical values related to percentages

    oai_token-act-pair · gpt-3.5-turbo

    references to statistical percentages and margins related to polling or survey data

    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
    iman
    -0.65
    indal
    -0.65
    gel
    -0.65
    leneck
    -0.64
    igl
    -0.62
    iva
    -0.60
    idan
    -0.59
    ãĥĦ
    -0.59
    uctor
    -0.59
    robe
    -0.59
    POSITIVE LOGITS
     points
    1.53
    points
    1.29
     point
    1.28
    point
    1.21
     Points
    1.17
    Points
    1.11
     pts
    1.10
    Point
    0.88
     digits
    0.87
     pointers
    0.84
    Activations Density 0.042%

    No Known Activations