Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6-RES-JB
    6. 16253
    Prev
    Next
    INDEX
    Explanations

    instances of the mention of a specific retailer - Barnes & Noble

    oai_token-act-pair · gpt-3.5-turbo

    references to bookstores and related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ufact
    -0.78
    ocular
    -0.76
    stress
    -0.71
    jah
    -0.69
    ibrary
    -0.69
    jury
    -0.67
    bish
    -0.66
    drm
    -0.64
    iquid
    -0.63
    icular
    -0.63
    POSITIVE LOGITS
    士
    0.83
     Forestry
    0.66
    :{
    0.63
    ãĤŃ
    0.63
    Ĥª
    0.62
    å°Ĩ
    0.62
     pains
    0.61
    ãĥ©ãĥ³
    0.61
     Polk
    0.58
    76561
    0.58
    Activations Density 0.157%

    No Known Activations