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

    Neuronpedia

    APICircuit 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. 4-RES-JB
    6. 22957
    Prev
    Next
    INDEX
    Explanations

    names of people, specifically focusing on the surname "Price"

    oai_token-act-pair · gpt-3.5-turbo

    references to the surname "Price."

    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
    RANT
    -0.88
    rum
    -0.83
    ATIONAL
    -0.72
    respons
    -0.71
    riend
    -0.70
     Glob
    -0.70
    udeb
    -0.70
    algia
    -0.69
    estern
    -0.69
    umbn
    -0.69
    POSITIVE LOGITS
    Price
    0.88
     premiums
    0.82
     Price
    0.81
     gou
    0.79
    onom
    0.74
     tags
    0.74
    killers
    0.73
     prices
    0.72
    hyde
    0.71
    Water
    0.70
    Activations Density 0.014%

    No Known Activations