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. 2-RES-JB
    6. 16805
    Prev
    Next
    INDEX
    Explanations

    names of public figures or individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of people and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nesday
    -0.81
    cule
    -0.78
    ationally
    -0.78
    ATIONAL
    -0.77
     Pats
    -0.75
    onial
    -0.74
     GI
    -0.69
    oso
    -0.68
    atile
    -0.67
    alde
    -0.66
    POSITIVE LOGITS
     Kejriwal
    1.05
    jriwal
    0.94
    Keefe
    0.76
     Clarkson
    0.73
    eters
    0.73
    ly
    0.71
    agher
    0.69
    lers
    0.69
    loo
    0.68
    zeb
    0.67
    Activations Density 0.009%

    No Known Activations