© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 21681
    Prev
    Next
    INDEX
    Explanations

    phrases related to institutions or organizations, especially those with the word "Commonwealth" and specific names like "Webster" or "Blackwell."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific organizations or locations

    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
    essee
    -0.93
    amaru
    -0.90
    abil
    -0.87
    abilities
    -0.87
    adelphia
    -0.86
    adows
    -0.83
    pee
    -0.82
    kers
    -0.82
    berman
    -0.81
    assic
    -0.81
    POSITIVE LOGITS
     Sins
    0.78
     Countries
    0.78
     Scientific
    0.73
     Brotherhood
    0.73
     Kingdoms
    0.71
     Scotia
    0.70
     Sisters
    0.68
     Parish
    0.68
     Institution
    0.67
     Isles
    0.65
    Activations Density 0.192%

    No Known Activations