© 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. 4-RES-JB
    11. 7410
    Prev
    Next
    INDEX
    Explanations

    actions involving physical force or effort, such as pushing, pulling, grabbing, and tugging

    oai_token-act-pair · gpt-3.5-turbo

    actions involving physical force or manipulation

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

    No Comments

    Negative Logits
     Surviv
    -0.77
    mun
    -0.74
    ãĥīãĥ©ãĤ´ãĥ³
    -0.73
     Broadcast
    -0.70
    Deal
    -0.70
    ãĥİ
    -0.69
    league
    -0.69
    天
    -0.68
    mberg
    -0.67
     Fallen
    -0.67
    POSITIVE LOGITS
     unconscious
    0.84
     joints
    0.79
     torches
    0.78
     glide
    0.78
    lasses
    0.77
     jerk
    0.76
     limp
    0.74
     downwards
    0.74
     gently
    0.73
     fists
    0.73
    Activations Density 0.141%

    No Known Activations