© 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. 8-RES-JB
    11. 4245
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical contact and communication

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "shake" and its variations, indicating actions of shaking or handshaking

    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
    swick
    -0.78
     [+
    -0.72
    minist
    -0.71
     Parenthood
    -0.70
    iary
    -0.67
    çĦ
    -0.66
    iband
    -0.66
    velength
    -0.65
    atar
    -0.65
     Minotaur
    -0.64
    POSITIVE LOGITS
    loo
    0.91
     hands
    0.81
    down
    0.78
    DOWN
    0.77
     shake
    0.76
     shaking
    0.75
     uncontroll
    0.74
     violently
    0.73
     shaky
    0.73
    buck
    0.73
    Activations Density 0.037%

    No Known Activations