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. 3-RES-JB
    6. 7796
    Prev
    Next
    INDEX
    Explanations

    the name "Paxton"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Paxton"

    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
    ename
    -0.83
    Reviewer
    -0.76
    taking
    -0.66
     livest
    -0.64
    hist
    -0.63
     masc
    -0.62
    uten
    -0.62
    tymology
    -0.60
    bes
    -0.59
    ã
    -0.59
    POSITIVE LOGITS
     Heath
    0.82
     Hale
    0.81
    bury
    0.78
    stown
    0.76
    ius
    0.75
    augh
    0.73
    igham
    0.73
    oked
    0.71
    combe
    0.70
    anus
    0.70
    Activations Density 0.010%

    No Known Activations