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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 11258
    Prev
    Next
    INDEX
    Explanations

    words related to an individual 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 @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xon
    -0.73
     arteries
    -0.70
    ħĭ
    -0.67
    ĸļ
    -0.66
     veins
    -0.66
     Defenders
    -0.65
     Underworld
    -0.62
    ©¶æ
    -0.62
    BuyableInstoreAndOnline
    -0.61
    ģ«
    -0.61
    POSITIVE LOGITS
    sburgh
    1.53
    itt
    1.04
    elle
    0.94
    leness
    0.92
    ake
    0.89
    orno
    0.89
    omo
    0.89
    sburg
    0.89
    rolled
    0.88
    ype
    0.87
    Activations Density 0.008%

    No Known Activations