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. 3952
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to mythology, literature, and popular media

    oai_token-act-pair · gpt-3.5-turbo

    prominent themes and titles of works related to hope, darkness, and conflict

    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
    etheless
    -0.75
    aditional
    -0.72
    aution
    -0.70
     citiz
    -0.69
    iably
    -0.63
    iosyn
    -0.63
     captcha
    -0.63
    plet
    -0.63
    ially
    -0.62
     reconc
    -0.62
    POSITIVE LOGITS
     fame
    1.01
     Remastered
    0.93
     Syndrome
    0.91
    âĦ¢
    0.87
     trilogy
    0.87
     syndrome
    0.86
     Volume
    0.84
     II
    0.84
     XIII
    0.80
    ulhu
    0.80
    Activations Density 0.202%

    No Known Activations