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. 3151
    Prev
    Next
    INDEX
    Explanations

    names of individuals, especially those with Eastern European origins

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names related to individuals

    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
    venant
    -0.82
    emouth
    -0.79
    mingham
    -0.73
    ocus
    -0.71
    gement
    -0.70
    lder
    -0.68
    itions
    -0.68
    istries
    -0.67
     stump
    -0.66
     crane
    -0.65
    POSITIVE LOGITS
    lov
    1.04
    rice
    0.85
    anian
    0.85
    daq
    0.79
    grad
    0.78
     Pav
    0.78
    oral
    0.75
     Yel
    0.73
     Polly
    0.73
    anski
    0.73
    Activations Density 0.021%

    No Known Activations