© 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. 4-RES-JB
    11. 523
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "pick up"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve the action of picking something up

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

    No Comments

    Negative Logits
    cius
    -0.77
    afia
    -0.73
    umn
    -0.70
    jah
    -0.66
    conn
    -0.66
    obi
    -0.65
    orius
    -0.65
    hidden
    -0.65
    ylene
    -0.64
    {"
    -0.64
    POSITIVE LOGITS
     stakes
    0.66
     poop
    0.64
     paddle
    0.64
     offense
    0.63
    outheast
    0.63
     steam
    0.63
     shards
    0.61
     Vintage
    0.60
    iques
    0.60
     Intercept
    0.60
    Activations Density 0.033%

    No Known Activations