© 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. 11-RES-JB
    11. 10110
    Prev
    Next
    INDEX
    Explanations

    proper nouns such as names of people, places, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and affiliations, particularly related to individuals and their backgrounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onies
    -0.78
    Otherwise
    -0.75
    OTHER
    -0.69
    Examples
    -0.68
    Accessory
    -0.67
    Translation
    -0.67
    respective
    -0.66
    pmwiki
    -0.65
    Higher
    -0.64
    tips
    -0.63
    POSITIVE LOGITS
     he
    1.03
     Mr
    0.90
     she
    0.90
     Dr
    0.78
     Conrad
    0.78
     Rodrigo
    0.77
     Prof
    0.77
     Jerome
    0.77
     Cecil
    0.76
     Denis
    0.75
    Activations Density 0.176%

    No Known Activations