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. 8-RES-JB
    6. 21940
    Prev
    Next
    INDEX
    Explanations

    the action of picking something up

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "pick up."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    croft
    -0.82
    umn
    -0.74
    obar
    -0.71
    conn
    -0.70
    ja
    -0.67
    afia
    -0.65
    ux
    -0.63
    ipedia
    -0.62
    oly
    -0.62
    irin
    -0.62
    POSITIVE LOGITS
     slack
    0.78
     pace
    0.78
    rights
    0.77
     steam
    0.77
     stitches
    0.74
     hitch
    0.69
     shards
    0.68
    earance
    0.68
    iques
    0.67
    speed
    0.66
    Activations Density 0.045%

    No Known Activations