© 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. 12136
    Prev
    Next
    INDEX
    Explanations

    references to a specific person named "Cav" or "Cavendish"

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals with the last name "Cav."

    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
    utenant
    -0.80
    ħĭ
    -0.75
    ĪĴ
    -0.72
    metry
    -0.68
     indicative
    -0.67
     rough
    -0.66
    ãĥ³ãĤ¸
    -0.64
    ters
    -0.63
    typ
    -0.62
    hirt
    -0.62
    POSITIVE LOGITS
    endish
    1.30
    illo
    1.09
    inelli
    1.04
    ity
    0.97
    iar
    0.94
     Cav
    0.93
    olini
    0.92
    illon
    0.92
    arella
    0.91
    lett
    0.89
    Activations Density 0.009%

    No Known Activations