© 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. 11258
    Prev
    Next
    INDEX
    Explanations

    words related to violent or extreme actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "acts" 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
    env
    -0.71
    puting
    -0.70
    rame
    -0.67
    UTC
    -0.65
    OVER
    -0.65
    edin
    -0.63
    board
    -0.63
     Loren
    -0.62
    DEM
    -0.61
    reference
    -0.61
    POSITIVE LOGITS
     acts
    3.66
     act
    2.28
     Acts
    2.14
     deeds
    1.59
     actions
    1.58
     acted
    1.54
    acts
    1.41
     behaves
    1.37
    Act
    1.31
     acting
    1.24
    Activations Density 0.012%

    No Known Activations