© 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. 0-RES-JB
    11. 1095
    Prev
    Next
    INDEX
    Explanations

    proper names specifically the last name "Peters."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Peters."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     swipe
    -0.83
    fly
    -0.81
    Space
    -0.70
     glitch
    -0.68
     sw
    -0.66
    atomic
    -0.65
    ãĤ´ãĥ³
    -0.64
     racer
    -0.62
     dat
    -0.62
     dance
    -0.62
    POSITIVE LOGITS
     Peters
    3.96
     Petersen
    1.31
     Lange
    1.16
     Peterson
    1.14
     Klein
    1.09
     Reid
    1.09
     McKenzie
    1.08
     Christensen
    1.08
     PET
    1.08
     Ips
    1.07
    Activations Density 0.007%

    No Known Activations