© 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. 0-RES-JB
    11. 19141
    Prev
    Next
    INDEX
    Explanations

    terms related to physical movement or action

    oai_token-act-pair · gpt-3.5-turbo

    references to social, political, or physical movements

    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
    vell
    -0.74
    worth
    -0.71
     ..........
    -0.70
    cox
    -0.69
    dds
    -0.68
     Downs
    -0.67
    esters
    -0.64
    ray
    -0.62
    :\
    -0.62
     Piper
    -0.61
    POSITIVE LOGITS
     movement
    3.77
     Movement
    2.89
     movements
    2.76
    move
    2.01
    Move
    1.82
     motion
    1.52
     Move
    1.43
     agitation
    1.37
     mobility
    1.37
     motions
    1.24
    Activations Density 0.026%

    No Known Activations