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. 2546
    Prev
    Next
    INDEX
    Explanations

    references to a specific person's name, "Baker"

    oai_token-act-pair · gpt-3.5-turbo

    the occurrences of the name "Baker"

    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
    Nazi
    -0.70
    neutral
    -0.69
    lex
    -0.66
    porting
    -0.63
    translation
    -0.62
    arching
    -0.61
    rise
    -0.61
    either
    -0.61
    American
    -0.61
    ERAL
    -0.60
    POSITIVE LOGITS
    loo
    1.39
     Baker
    1.15
     nodd
    0.86
    VPN
    0.85
    ieri
    0.82
    keley
    0.75
    leneck
    0.73
    tis
    0.71
    gren
    0.70
    icum
    0.70
    Activations Density 0.012%

    No Known Activations