© 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. 10269
    Prev
    Next
    INDEX
    Explanations

    proper names, specifically "Emily" and "Earl"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, particularly "Emily" and "Earl."

    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
    geon
    -0.75
    uran
    -0.66
    ñ
    -0.65
    edit
    -0.65
    istan
    -0.65
    giving
    -0.64
    hao
    -0.63
    thro
    -0.62
    arak
    -0.61
    ering
    -0.60
    POSITIVE LOGITS
    sburg
    1.03
     Dickinson
    0.85
    izabeth
    0.82
     Ack
    0.82
    ottesville
    0.82
    otte
    0.73
    ivered
    0.73
    phia
    0.71
    oided
    0.70
    issance
    0.69
    Activations Density 0.136%

    No Known Activations