© 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. 0-RES-JB
    11. 6610
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical movement or actions

    oai_token-act-pair · gpt-3.5-turbo

    the substring "mo" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Terrorism
    -0.71
    Hack
    -0.67
    SPONSORED
    -0.67
    ounter
    -0.67
    ateful
    -0.67
     Parallel
    -0.65
    itism
    -0.64
    BOOK
    -0.64
    alth
    -0.63
    ipers
    -0.62
    POSITIVE LOGITS
     mo
    3.96
    mo
    1.77
    Mo
    1.74
     Mo
    1.50
     mos
    1.31
     Moose
    1.30
     MO
    1.28
     fri
    1.17
     gro
    1.11
     moan
    1.11
    Activations Density 0.006%

    No Known Activations