© 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. 10-RES-JB
    11. 2743
    Prev
    Next
    INDEX
    Explanations

    sports scores and game outcomes

    oai_token-act-pair · gpt-3.5-turbo

    numerals, particularly those associated with sports scores and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     privilege
    -0.64
    etsk
    -0.60
    rection
    -0.60
     suspended
    -0.59
    usp
    -0.58
    phant
    -0.57
    riot
    -0.56
    arb
    -0.56
     ration
    -0.55
     imported
    -0.55
    POSITIVE LOGITS
    %-
    0.83
    ½
    0.77
    89
    0.76
    95
    0.76
    63
    0.74
    73
    0.72
    91
    0.72
    98
    0.71
    79
    0.71
    96
    0.71
    Activations Density 0.065%

    No Known Activations