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. 0-RES-JB
    6. 16235
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific person's name "Gaku"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific Japanese names or terms related to a particular context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     toll
    -0.72
     calendar
    -0.67
     Triumph
    -0.65
     cycles
    -0.65
     qualified
    -0.65
     Martha
    -0.61
     Aud
    -0.60
     miscarriage
    -0.59
     fer
    -0.59
     surviv
    -0.59
    POSITIVE LOGITS
    aku
    4.63
    etsu
    1.59
    oku
    1.58
    akuya
    1.30
    ako
    1.25
    itsu
    1.19
    uku
    1.18
    oko
    1.16
    eki
    1.14
    ashi
    1.14
    Activations Density 0.014%

    No Known Activations