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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 3312
    Prev
    Next
    INDEX
    Explanations

    references to specific organizations or entities, particularly Omega and Sigma Nu

    oai_token-act-pair · gpt-3.5-turbo

    references to Greek life or fraternity-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    puter
    -0.92
    ebook
    -0.86
    ulatory
    -0.84
    ibrary
    -0.80
    erers
    -0.80
    olds
    -0.78
    erer
    -0.75
    OWS
    -0.75
    itcher
    -0.73
    ================================================================
    -0.73
    POSITIVE LOGITS
    ilon
    1.48
     Eps
    1.21
     Sigma
    1.09
     Phi
    1.07
     Centauri
    1.06
     Gamma
    0.98
     Delta
    0.95
     Beta
    0.88
     Kappa
    0.87
     Alpha
    0.86
    Activations Density 0.016%

    No Known Activations