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. 10-RES-JB
    6. 19409
    Prev
    Next
    INDEX
    Explanations

    keywords related to computer hash functions

    oai_token-act-pair · gpt-3.5-turbo

    references to hashtags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ong
    -0.72
     Patton
    -0.69
     Parish
    -0.68
     Superior
    -0.66
     Kore
    -0.65
    ials
    -0.63
     Shroud
    -0.62
    ufact
    -0.61
     Archangel
    -0.61
     Heavenly
    -0.60
    POSITIVE LOGITS
    tag
    1.24
    tags
    1.24
    imoto
    1.07
    cash
    0.99
    bang
    0.94
    hash
    0.88
    yll
    0.82
     tag
    0.80
    brown
    0.80
    mi
    0.76
    Activations Density 0.031%

    No Known Activations