© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 17228
    Prev
    Next
    INDEX
    Explanations

    names of people, particularly recurring names such as "Carly", "Christy", and "Jenny"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Carly"

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

    No Comments

    Negative Logits
     guiActiveUnfocused
    -0.75
    SPONSORED
    -0.72
    é¾į
    -0.70
    EngineDebug
    -0.67
    shapeshifter
    -0.66
     Cosponsors
    -0.66
    HCR
    -0.66
    Reviewer
    -0.65
     Explorer
    -0.63
    animous
    -0.62
    POSITIVE LOGITS
     Fiorina
    1.12
     Carly
    0.97
     Rae
    0.97
    ttle
    0.82
    rics
    0.81
    plates
    0.76
    ¸
    0.74
    zeb
    0.73
    utical
    0.71
     stalls
    0.70
    Activations Density 0.008%

    No Known Activations