© 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. 4-RES-JB
    11. 23973
    Prev
    Next
    INDEX
    Explanations

    sports-related statistics and player names

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics or data points in a structured format

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

    No Comments

    Negative Logits
    DragonMagazine
    -0.88
    ensibly
    -0.71
    aminer
    -0.67
    oc
    -0.66
    afety
    -0.66
    OPLE
    -0.65
    onomic
    -0.63
    uine
    -0.62
    ulously
    -0.62
    cul
    -0.62
    POSITIVE LOGITS
     Kart
    0.70
     Trip
    0.66
     Madagascar
    0.60
     Ala
    0.59
     Deals
    0.59
     Barbarian
    0.58
     Martial
    0.57
     rows
    0.57
     Sul
    0.57
     Spells
    0.56
    Activations Density 0.118%

    No Known Activations