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. 21269
    Prev
    Next
    INDEX
    Explanations

    names of individuals involved in various news events

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals involved in a specific event or situation

    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
    fare
    -0.75
    romancer
    -0.75
    ishers
    -0.75
    soDeliveryDate
    -0.74
    ãĥĩãĤ£
    -0.73
    #$
    -0.71
    urbed
    -0.69
    acle
    -0.68
    estones
    -0.64
     Somerset
    -0.64
    POSITIVE LOGITS
    irez
    1.11
     Alvarez
    0.95
     Ramos
    0.94
     Reyes
    0.92
     Gutierrez
    0.91
     Flores
    0.90
     Ortiz
    0.90
     Diaz
    0.88
     Gonzalez
    0.87
    quez
    0.87
    Activations Density 0.032%

    No Known Activations