Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 15896
    Prev
    Next
    INDEX
    Explanations

    names of people or characters

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, particularly those beginning with "Isa" or "Isaiah."

    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
    20439
    -0.90
    essee
    -0.82
    fact
    -0.76
    lease
    -0.72
    llular
    -0.70
    roleum
    -0.67
    iment
    -0.67
    duct
    -0.66
    chnology
    -0.66
    )=(
    -0.66
    POSITIVE LOGITS
    iah
    1.03
     Yose
    1.02
     Judah
    1.02
     Canaan
    0.96
     Netanyahu
    0.91
     Cohen
    0.89
     Stern
    0.86
     ×
    0.84
     Torah
    0.83
     Coh
    0.82
    Activations Density 0.068%

    No Known Activations