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. 20982
    Prev
    Next
    INDEX
    Explanations

    the phrase "one of" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to singular entities or items in a context that emphasizes their individuality or uniqueness

    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
     poles
    -0.65
     tractor
    -0.63
     bargain
    -0.62
     resil
    -0.62
     bearings
    -0.61
     buggy
    -0.60
    osate
    -0.59
     umb
    -0.59
     sword
    -0.59
     burden
    -0.59
    POSITIVE LOGITS
    else
    0.80
    ctory
    0.79
     whatsoever
    0.78
     else
    0.75
    etimes
    0.75
    kaya
    0.74
     imaginable
    0.73
    Access
    0.71
    astical
    0.70
    other
    0.69
    Activations Density 0.069%

    No Known Activations