© 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. 3-RES-JB
    11. 12254
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific person named "Whittaker."

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Whittaker."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.76
    ħĭ
    -0.67
    ĨĴ
    -0.64
    xon
    -0.63
     arteries
    -0.63
    xual
    -0.62
     infringing
    -0.60
     womb
    -0.60
     regress
    -0.59
    ©¶æ
    -0.59
    POSITIVE LOGITS
    sburgh
    1.58
    leness
    0.93
    sburg
    0.92
    ype
    0.90
    ents
    0.89
    robe
    0.89
    ety
    0.88
    ake
    0.88
    omo
    0.88
    ito
    0.88
    Activations Density 0.008%

    No Known Activations