© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-RES-JB
    11. 5730
    Prev
    Next
    INDEX
    Explanations

    questions or statements regarding various topics, including reputation, faith, home ownership, political figures, democracy, and more

    oai_token-act-pair · gpt-3.5-turbo

    significant concepts and themes related to ethics and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     greets
    -0.73
    Previous
    -0.72
    ook
    -0.70
    çīĪ
    -0.69
    regate
    -0.68
    gain
    -0.68
    export
    -0.67
    edIn
    -0.66
    phabet
    -0.64
    details
    -0.64
    POSITIVE LOGITS
     supposed
    1.05
     irrelevant
    0.99
     useless
    0.98
     preferable
    0.98
     worth
    0.96
     contagious
    0.96
     appealing
    0.94
     feasible
    0.94
     indicative
    0.93
     inherently
    0.93
    Activations Density 0.283%

    No Known Activations