© 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. 17323
    Prev
    Next
    INDEX
    Explanations

    names related to the name "Jeff"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Jeff" and its variations in the text

    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
     womb
    -0.72
     CODE
    -0.68
    atform
    -0.67
    xual
    -0.65
     Instr
    -0.62
     outgoing
    -0.62
     IMAGES
    -0.61
    houses
    -0.59
     abundance
    -0.58
    ktop
    -0.57
    POSITIVE LOGITS
    reys
    1.37
    ery
    1.37
    rey
    1.35
    eries
    1.33
    erey
    1.28
    erson
    1.21
     Bezos
    1.11
    ries
    1.00
    ress
    1.00
     Sessions
    0.98
    Activations Density 0.028%

    No Known Activations