© 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. 7-RES-JB
    11. 1597
    Prev
    Next
    INDEX
    Explanations

    text related to different levels or categories

    oai_token-act-pair · gpt-3.5-turbo

    references to LCD technology or related components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.88
    é¾įåĸļ士
    -0.77
    shake
    -0.75
    ably
    -0.73
     Taj
    -0.72
    thing
    -0.70
    liness
    -0.69
    ãĥĥãĥĪ
    -0.68
    fell
    -0.67
    lers
    -0.63
    POSITIVE LOGITS
    ateral
    0.94
    creen
    0.90
    orem
    0.88
    aughter
    0.86
    VD
    0.83
    aution
    0.82
    uesday
    0.80
    ategory
    0.79
    VO
    0.78
    anyon
    0.78
    Activations Density 0.033%

    No Known Activations