© 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. 4-RES-JB
    11. 10321
    Prev
    Next
    INDEX
    Explanations

    terms related to a variety of professional industries and sports

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with various sports and entertainment disciplines

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

    No Comments

    Negative Logits
    eret
    -0.72
     Hai
    -0.67
     Vin
    -0.64
     Bravo
    -0.63
     Hamas
    -0.62
    xit
    -0.62
     Shinra
    -0.61
     Fukushima
    -0.61
     Kaepernick
    -0.61
     Muller
    -0.60
    POSITIVE LOGITS
     historian
    0.95
     consultancy
    0.92
    indust
    0.88
     circles
    0.87
     industry
    0.87
     historians
    0.87
     nerds
    0.86
     professionals
    0.85
     jargon
    0.85
     literacy
    0.85
    Activations Density 0.479%

    No Known Activations