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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11369
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical actions or activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to actions of picking up and pushing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Nieto
    -0.78
     Cabrera
    -0.68
     Princ
    -0.66
     Monstrous
    -0.66
     tears
    -0.66
     Griffith
    -0.65
     Pione
    -0.65
     Canad
    -0.63
     Principal
    -0.62
     Fallen
    -0.61
    POSITIVE LOGITS
    cart
    1.17
    down
    1.05
    mat
    1.00
    ups
    0.99
    ety
    0.96
    axe
    0.95
    mob
    0.94
    downs
    0.93
    offs
    0.92
    stick
    0.90
    Activations Density 0.137%

    No Known Activations