© 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. 11-RES-JB
    11. 7124
    Prev
    Next
    INDEX
    Explanations

    words related to movement and physical actions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GoPro
    -0.68
     Fiesta
    -0.68
    Kids
    -0.67
     Collider
    -0.67
    cial
    -0.66
     Cassidy
    -0.64
     Activities
    -0.63
    ggies
    -0.62
     Environmental
    -0.62
    classic
    -0.62
    POSITIVE LOGITS
     thence
    1.50
     forth
    1.48
     hither
    1.40
     upon
    1.31
     unto
    1.30
     thereto
    1.20
     boldly
    1.19
     anew
    1.19
     irresist
    1.13
     perpend
    1.11
    Activations Density 0.218%

    No Known Activations