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

    Neuronpedia

    Jacobian LensNEW
    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. 20702
    Prev
    Next
    INDEX
    Explanations

    information related to various outlets or sources where content can be developed or featured

    oai_token-act-pair · gpt-3.5-turbo

    references to various entities, locations, and themes related to media, culture, and society

    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
     seiz
    -0.60
    apego
    -0.59
    amera
    -0.59
    yss
    -0.58
    ensibly
    -0.58
    specific
    -0.56
    aeper
    -0.54
     brut
    -0.54
    ogie
    -0.53
     looph
    -0.53
    POSITIVE LOGITS
    .(
    0.86
    \.
    0.83
    *.
    0.81
    )).
    0.81
    .''
    0.80
    $.
    0.80
     ;)
    0.80
    .).
    0.80
     attRot
    0.79
    .''.
    0.78
    Activations Density 0.870%

    No Known Activations