© 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. 1741
    Prev
    Next
    INDEX
    Explanations

    text related to legal and political discourse

    oai_token-act-pair · gpt-3.5-turbo

    expressions of plans, decisions, or intentions

    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
    !'
    -0.69
     Illust
    -0.67
     Whilst
    -0.66
    '),
    -0.65
     whilst
    -0.65
    schild
    -0.63
    ategor
    -0.62
     Martial
    -0.62
     wretched
    -0.61
    aganda
    -0.60
    POSITIVE LOGITS
    wcs
    0.84
     counseling
    0.81
     outwe
    0.74
    ¬¼
    0.72
     counselors
    0.72
     anecd
    0.69
     "[
    0.68
    forums
    0.66
    aukee
    0.66
     statewide
    0.65
    Activations Density 1.313%

    No Known Activations