© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 2993
    Prev
    Next
    INDEX
    Explanations

    locations and actions related to movement, especially walking and driving

    oai_token-act-pair · gpt-3.5-turbo

    actions or activities related to movement or engagement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phies
    -0.72
    ema
    -0.65
    lands
    -0.62
    cknowled
    -0.61
    pora
    -0.59
    rust
    -0.59
    aryn
    -0.58
    ulnerability
    -0.58
    ogene
    -0.57
    rely
    -0.57
    POSITIVE LOGITS
    itored
    0.77
    heses
    0.70
    tips
    0.68
    seless
    0.67
    Pand
    0.66
    Sov
    0.65
    Constructed
    0.65
     exha
    0.62
    RAG
    0.62
     Classes
    0.61
    Activations Density 0.190%

    No Known Activations