© 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. 10-RES-JB
    11. 14182
    Prev
    Next
    INDEX
    Explanations

    names that start with "Jo"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals and teams

    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
    yip
    -0.69
    enegger
    -0.66
    uously
    -0.61
     Circus
    -0.59
    uits
    -0.56
    uous
    -0.56
     pasta
    -0.56
     present
    -0.55
    fires
    -0.55
     spill
    -0.55
    POSITIVE LOGITS
    aku
    0.83
    lyn
    0.66
    Jr
    0.66
    angan
    0.66
    isha
    0.66
    emp
    0.65
    cott
    0.65
    steen
    0.64
    sburg
    0.64
    ãģĨ
    0.64
    Activations Density 0.114%

    No Known Activations