© 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. 3-RES-JB
    11. 11992
    Prev
    Next
    INDEX
    Explanations

    words related to different zones in a sports context

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "zone" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HCR
    -0.95
    sonian
    -0.89
    issance
    -0.85
    teness
    -0.82
    verified
    -0.82
    nant
    -0.81
    ensional
    -0.81
    akuya
    -0.80
    TON
    -0.79
    lder
    -0.77
    POSITIVE LOGITS
     zone
    1.03
     zones
    0.93
     blitz
    0.81
     Zone
    0.77
     congestion
    0.71
     bunker
    0.69
     jerk
    0.69
     creeps
    0.67
     penetration
    0.65
     conversions
    0.65
    Activations Density 0.006%

    No Known Activations