© 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. 6-RES-JB
    11. 12280
    Prev
    Next
    INDEX
    Explanations

    proper nouns including names and surnames starting with the letter "S" and "G" at the activation values are above 8

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, specifically artists and public figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Newsletter
    -0.74
     crop
    -0.61
    RIC
    -0.58
    é¾įå
    -0.57
    ruary
    -0.56
     forgiveness
    -0.56
     NEC
    -0.56
    hift
    -0.55
     hindsight
    -0.55
    Cub
    -0.53
    POSITIVE LOGITS
    uren
    0.80
    atu
    0.79
    ihilation
    0.79
    eden
    0.76
    wen
    0.75
    bilt
    0.73
    bek
    0.73
    ouver
    0.73
    burgh
    0.72
    esy
    0.71
    Activations Density 0.068%

    No Known Activations