© 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. 1-RES-JB
    11. 24230
    Prev
    Next
    INDEX
    Explanations

    names – specifically, the name "Carey"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, particularly "Carey" and "Wyatt."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĥãĥī
    -0.78
    utra
    -0.77
    ordered
    -0.75
    ordinate
    -0.72
    udeb
    -0.69
    und
    -0.69
    umat
    -0.69
    ibli
    -0.68
    Iraq
    -0.68
    ailand
    -0.68
    POSITIVE LOGITS
     Carey
    1.36
     Howe
    0.77
     Burnett
    0.74
    mson
    0.72
    tti
    0.71
     Pwr
    0.70
     Feldman
    0.70
     Abrams
    0.69
    mons
    0.67
     Dixon
    0.67
    Activations Density 0.006%

    No Known Activations