© 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. 12788
    Prev
    Next
    INDEX
    Explanations

    records or achievements, particularly in sports

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sports statistics and records

    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
    Pros
    -0.79
    Plan
    -0.67
    olls
    -0.66
     spoiler
    -0.65
    Econom
    -0.61
    fact
    -0.61
    MODE
    -0.61
    plan
    -0.61
    advant
    -0.61
     PLAN
    -0.60
    POSITIVE LOGITS
    sets
    0.87
     consecutive
    0.81
    İĭ
    0.80
     career
    0.78
     receptions
    0.76
     assists
    0.76
     tying
    0.70
     streaks
    0.69
     homers
    0.68
     rushing
    0.66
    Activations Density 0.144%

    No Known Activations