© 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. 21118
    Prev
    Next
    INDEX
    Explanations

    calls to action in text, specifically prompting to select or subscribe to something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to making choices or selections

    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
    ĸļ
    -0.98
    naissance
    -0.86
    cule
    -0.83
    issance
    -0.82
    cular
    -0.82
    behind
    -0.80
    visible
    -0.76
    interrupted
    -0.75
    ģĸ
    -0.74
    Requires
    -0.74
    POSITIVE LOGITS
     wisely
    1.02
     randomly
    0.88
     preset
    0.87
     option
    0.80
     Cosponsors
    0.76
     winners
    0.76
     chosen
    0.76
     winner
    0.74
     preferred
    0.73
     lottery
    0.73
    Activations Density 0.247%

    No Known Activations