© 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. 11-RES-JB
    11. 18112
    Prev
    Next
    INDEX
    Explanations

    words related to business, leadership, and community growth

    oai_token-act-pair · gpt-3.5-turbo

    mentions of societal changes or cultural transformations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĢ
    -1.07
    âĢIJ
    -0.97
     horrend
    -0.97
     âĢ
    -0.96
     incompet
    -0.86
    Invalid
    -0.86
    Fuck
    -0.86
    ··
    -0.86
     arbitrarily
    -0.85
    âĨ
    -0.83
    POSITIVE LOGITS
     mentors
    0.98
     alumni
    0.93
     collaborations
    0.85
     Wildcats
    0.80
     Insp
    0.79
     millennials
    0.79
     scholarships
    0.78
     versatility
    0.77
     friendships
    0.77
     Asheville
    0.76
    Activations Density 0.946%

    No Known Activations