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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 24025
    Prev
    Next
    INDEX
    Explanations

    names and surnames

    oai_token-act-pair · gpt-3.5-turbo

    names and titles related to events or individuals in sports and entertainment contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eater
    -0.72
    GF
    -0.71
     kitchens
    -0.67
    geon
    -0.64
    essor
    -0.62
     arrang
    -0.62
    tell
    -0.61
    earcher
    -0.61
     synthetic
    -0.60
    fixed
    -0.59
    POSITIVE LOGITS
    ItemTracker
    0.95
    gio
    0.83
    rious
    0.82
    uyomi
    0.77
    ratulations
    0.76
    lihood
    0.74
    imize
    0.74
    adish
    0.73
    PsyNetMessage
    0.73
    osate
    0.73
    Activations Density 0.038%

    No Known Activations