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. 1-RES-JB
    6. 15013
    Prev
    Next
    INDEX
    Explanations

    Japanese names and possibly locations

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals associated with a specific cultural context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pages
    -0.73
     funn
    -0.69
    lain
    -0.68
    respons
    -0.67
    drawn
    -0.66
     incompet
    -0.61
    */(
    -0.59
    space
    -0.59
     Angry
    -0.59
    umbnails
    -0.58
    POSITIVE LOGITS
    umi
    1.26
    uri
    1.03
    aki
    0.96
    ás
    0.96
    atsu
    0.92
    oto
    0.87
    ya
    0.86
    imura
    0.86
    qa
    0.84
    ako
    0.83
    Activations Density 0.007%

    No Known Activations