Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7570
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to different entities or individuals

    oai_token-act-pair · gpt-3.5-turbo

    entities related to organizations, movements, or political affiliations

    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
    untarily
    -0.64
     consent
    -0.60
     whisper
    -0.59
    onym
    -0.59
    eatured
    -0.58
     simulated
    -0.58
    ezvous
    -0.57
    alyses
    -0.57
     flaw
    -0.55
    uphem
    -0.54
    POSITIVE LOGITS
     sake
    0.96
     considering
    0.91
    é¾įåĸļ士
    0.78
     because
    0.77
    erning
    0.75
    especially
    0.75
     lovers
    0.73
     concerned
    0.72
     morale
    0.72
     purposes
    0.72
    Activations Density 0.438%

    No Known Activations