© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 2496
    Prev
    Next
    INDEX
    Explanations

    words related to violence and conflict

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    phrases related to crowds or groups of people

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     lying
    -0.67
     associ
    -0.64
     suited
    -0.63
    DEN
    -0.61
     recogn
    -0.60
     prone
    -0.60
     pred
    -0.60
     misleading
    -0.59
     brid
    -0.59
     alive
    -0.58
    POSITIVE LOGITS
    ongs
    1.44
    ifty
    1.41
    ift
    1.36
    ashing
    1.36
    ice
    1.27
    ashed
    1.25
    ills
    1.22
    usters
    1.18
    ong
    1.18
    ashes
    1.15
    Activations Density 0.019%

    No Known Activations