© 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. 8-RES-JB
    11. 6063
    Prev
    Next
    INDEX
    Explanations

    sports seasons expressed in a specific format (year1-year2)

    oai_token-act-pair · gpt-3.5-turbo

    references to specific sports seasons and their associated statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bones
    -0.67
    pload
    -0.66
    chu
    -0.63
    imeters
    -0.63
     Swanson
    -0.63
     answ
    -0.62
    ographer
    -0.61
    BILITY
    -0.61
     Stones
    -0.59
    xus
    -0.59
    POSITIVE LOGITS
     onwards
    0.80
     editions
    0.76
     Outlook
    0.76
     season
    0.76
     edition
    0.71
     cycle
    0.70
     timeframe
    0.67
     attRot
    0.66
     seasons
    0.65
    iphate
    0.65
    Activations Density 0.046%

    No Known Activations