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. 9728
    Prev
    Next
    INDEX
    Explanations

    the surname "Soderbergh."

    oai_token-act-pair · gpt-3.5-turbo

    words that are related to the concept of identity or personhood

    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
     Gazette
    -0.73
     Acts
    -0.64
     Lovecraft
    -0.64
     Yoga
    -0.59
     Bethlehem
    -0.59
     Fact
    -0.57
    Fra
    -0.56
     Canterbury
    -0.55
    drawn
    -0.55
    ups
    -0.54
    POSITIVE LOGITS
    oder
    1.41
    ception
    0.97
    rors
    0.96
    ode
    0.91
    aton
    0.90
    oding
    0.89
    ror
    0.88
    acher
    0.88
    quist
    0.86
    WithNo
    0.86
    Activations Density 0.007%

    No Known Activations