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. 23769
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a strong opinion or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    the word "so" in various contexts

    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
     Advantage
    -0.60
     Peninsula
    -0.58
     Incarn
    -0.57
    Footnote
    -0.57
    "],"
    -0.57
     Cabinet
    -0.56
     Altern
    -0.56
     Organisation
    -0.55
     Halls
    -0.53
    intosh
    -0.53
    POSITIVE LOGITS
    oooo
    1.25
    bered
    1.22
    ooo
    1.17
    apy
    1.09
    oths
    1.06
    oooooooo
    1.05
    othes
    1.01
    othe
    0.99
     far
    0.98
    othing
    0.95
    Activations Density 0.048%

    No Known Activations