Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 23558
    Prev
    Next
    INDEX
    Explanations

    nouns related to people's names, specifically the name "Kent."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Kent."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ream
    -0.71
     CR
    -0.70
    ı
    -0.67
    rating
    -0.67
    imil
    -0.67
     capac
    -0.67
    CR
    -0.65
    urrencies
    -0.64
     ratings
    -0.64
     sensitivity
    -0.63
    POSITIVE LOGITS
     Kent
    3.81
    Kent
    2.69
     Essex
    1.60
     Sussex
    1.52
     Dover
    1.46
     Devon
    1.45
     Surrey
    1.36
     Kentucky
    1.34
     Berks
    1.29
     Somerset
    1.28
    Activations Density 0.018%

    No Known Activations