© 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 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. 8-RES-JB
    11. 19354
    Prev
    Next
    INDEX
    Explanations

    terms related to the movement of objects or living beings

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of movement

    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
    ihil
    -0.75
    ãĤ©
    -0.72
    rypt
    -0.70
    unts
    -0.70
    CLA
    -0.66
    nect
    -0.65
    aylor
    -0.65
    pled
    -0.65
    dds
    -0.64
    GE
    -0.64
    POSITIVE LOGITS
     motions
    0.93
     movements
    0.87
    peed
    0.86
     motion
    0.84
    able
    0.80
     patterns
    0.79
    overs
    0.77
    letal
    0.75
     Disorders
    0.74
     sickness
    0.73
    Activations Density 0.071%

    No Known Activations