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. 6-RES-JB
    6. 5641
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a location or entity named "Wrigley"

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "rig"

    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
     Leilan
    -0.82
    peak
    -0.73
    birth
    -0.69
    etheless
    -0.68
     Despair
    -0.68
     Virgin
    -0.65
     Worlds
    -0.64
     Perspective
    -0.62
     Pry
    -0.62
     Shore
    -0.61
    POSITIVE LOGITS
    uez
    1.37
    orously
    1.09
    ging
    1.07
    endum
    1.01
    ardless
    1.01
    rig
    1.01
    gling
    1.00
    gers
    0.99
    iosity
    0.97
    uers
    0.95
    Activations Density 0.015%

    No Known Activations