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. 8-RES-JB
    6. 9579
    Prev
    Next
    INDEX
    Explanations

    events or ceremonies

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to events or gatherings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    catentry
    -0.84
    BILITIES
    -0.83
    д
    -0.76
     experimented
    -0.75
    Ò
    -0.74
     teasp
    -0.73
    phabet
    -0.72
    lins
    -0.68
    vertising
    -0.67
    edin
    -0.67
    POSITIVE LOGITS
     Marriott
    1.00
     Dull
    0.89
     Pavilion
    0.89
     Plaza
    0.88
     Mansion
    0.84
     Eag
    0.82
     Arlington
    0.82
     downtown
    0.81
    rium
    0.81
     pav
    0.79
    Activations Density 0.238%

    No Known Activations