© 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. 11-RES-JB
    11. 24120
    Prev
    Next
    INDEX
    Explanations

    sports-related terms and contract-related language

    oai_token-act-pair · gpt-3.5-turbo

    references to player contracts and team management decisions

    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
    £ı
    -0.70
    plin
    -0.66
    chin
    -0.66
     Dew
    -0.63
    correct
    -0.62
    average
    -0.61
     Illust
    -0.61
    ĸļ
    -0.61
     correction
    -0.60
     invent
    -0.60
    POSITIVE LOGITS
     contractual
    1.19
     contract
    1.09
     negotiations
    1.06
     renegoti
    1.05
     farewell
    1.01
     commitments
    0.95
     agent
    0.94
     retirement
    0.94
    contract
    0.92
     opting
    0.90
    Activations Density 0.536%

    No Known Activations