© 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. 21249
    Prev
    Next
    INDEX
    Explanations

    phrases or questions related to random or hypothetical scenarios

    oai_token-act-pair · gpt-3.5-turbo

    sentences that contain questions or rhetorical inquiries

    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
     dialect
    -0.74
     embassy
    -0.71
    Forge
    -0.68
     unilaterally
    -0.67
    ilib
    -0.67
     misrepresent
    -0.66
     UNCLASSIFIED
    -0.64
     unilateral
    -0.63
     materially
    -0.61
     bloc
    -0.61
    POSITIVE LOGITS
     Turns
    0.79
    Enter
    0.76
     Mehran
    0.72
    joice
    0.72
    hiro
    0.71
    Luckily
    0.67
     Garmin
    0.67
    STON
    0.66
     Franch
    0.65
    Thankfully
    0.65
    Activations Density 0.825%

    No Known Activations