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. 12847
    Prev
    Next
    INDEX
    Explanations

    names of famous individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of notable individuals and references to performance or reputation

    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
    obo
    -0.71
    istically
    -0.70
    ño
    -0.66
    iru
    -0.66
    ASH
    -0.65
    iso
    -0.64
    gdala
    -0.62
     Seg
    -0.60
    emia
    -0.60
    llah
    -0.60
    POSITIVE LOGITS
     Phelps
    0.95
     Manson
    0.89
    icka
    0.87
    mans
    0.82
    achusetts
    0.79
    mann
    0.79
    liga
    0.78
    ter
    0.77
    itudes
    0.77
    enium
    0.76
    Activations Density 0.024%

    No Known Activations