© 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. 11-RES-JB
    11. 24178
    Prev
    Next
    INDEX
    Explanations

    names of individuals named Brett

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Brett"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oting
    -0.81
    criptions
    -0.81
    DER
    -0.73
    CVE
    -0.71
    cribed
    -0.67
    horse
    -0.65
    OTE
    -0.64
    pir
    -0.61
    isable
    -0.61
    vier
    -0.60
    POSITIVE LOGITS
     Kavanaugh
    1.14
     Fav
    1.08
    aneers
    0.82
    odox
    0.82
     McKay
    0.81
     Hull
    0.81
     Lancaster
    0.79
    anos
    0.79
    olini
    0.76
     Myers
    0.76
    Activations Density 0.037%

    No Known Activations