© 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. 2-RES-JB
    11. 9463
    Prev
    Next
    INDEX
    Explanations

    references to fraternity-related activities or events

    oai_token-act-pair · gpt-3.5-turbo

    references to fraternities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    recorded
    -0.78
    othy
    -0.76
     Overs
    -0.72
    inez
    -0.70
     Accessed
    -0.69
    stroke
    -0.69
    twitter
    -0.68
     Nanto
    -0.68
     Kers
    -0.67
    held
    -0.65
    POSITIVE LOGITS
     fraternity
    1.34
    ority
    1.11
    aternity
    0.97
     Phi
    0.96
     alumni
    0.89
     initiation
    0.82
     Sigma
    0.80
     sor
    0.79
     citiz
    0.79
     circle
    0.77
    Activations Density 0.008%

    No Known Activations