© 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. 1-RES-JB
    11. 20356
    Prev
    Next
    INDEX
    Explanations

    names of a particular person (Brendan) that might be important or of interest in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the name "Brendan."

    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
    intend
    -0.77
    LECT
    -0.76
    ball
    -0.71
     volleyball
    -0.68
    SPONSORED
    -0.67
    indu
    -0.67
    BOOK
    -0.66
    UV
    -0.66
    VOL
    -0.65
    grades
    -0.64
    POSITIVE LOGITS
     Brendan
    1.03
    heses
    0.89
    ufact
    0.85
    nered
    0.80
    agraph
    0.78
    Brend
    0.77
    atical
    0.74
    hesis
    0.74
    etooth
    0.73
    ermott
    0.73
    Activations Density 0.006%

    No Known Activations