© 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. 21247
    Prev
    Next
    INDEX
    Explanations

    names of people and their related legal issues

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "is" in various contexts

    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
    fail
    -0.68
    inav
    -0.66
    rous
    -0.66
     peaks
    -0.64
     wastes
    -0.64
     refrain
    -0.63
     heavens
    -0.61
    ],[
    -0.61
    ossom
    -0.61
     excess
    -0.60
    POSITIVE LOGITS
     currently
    1.12
     credited
    1.03
     now
    1.02
     slated
    1.02
    senal
    0.99
    cussion
    0.98
     barred
    0.98
     suing
    0.97
     congratulated
    0.92
     also
    0.92
    Activations Density 0.435%

    No Known Activations