© 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. 10-RES-JB
    11. 13859
    Prev
    Next
    INDEX
    Explanations

    terms related to attention, recognition, and awareness

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to attention and coverage of specific topics or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agate
    -0.80
    tta
    -0.72
    ©¶æ
    -0.71
     Alone
    -0.71
    artifacts
    -0.69
    vable
    -0.68
    puter
    -0.68
    hid
    -0.67
    Plan
    -0.66
    ramid
    -0.66
    POSITIVE LOGITS
     attention
    1.59
     notoriety
    1.42
     acclaim
    1.41
     publicity
    1.33
     applause
    1.32
     traction
    1.25
     ire
    1.24
     accol
    1.22
     praise
    1.19
     scorn
    1.15
    Activations Density 0.183%

    No Known Activations