© 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. 1-RES-JB
    11. 14513
    Prev
    Next
    INDEX
    Explanations

    words related to acts of aggression or violence

    oai_token-act-pair · gpt-3.5-turbo

    references to attacks, particularly in a violent or aggressive context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zl
    -0.65
    tz
    -0.62
    ETA
    -0.61
    atom
    -0.60
     Marketable
    -0.60
    Vert
    -0.59
     Supplementary
    -0.58
    Zip
    -0.58
    theless
    -0.57
    glomer
    -0.57
    POSITIVE LOGITS
    attack
    1.16
     attack
    1.09
     attacks
    0.96
    Attack
    0.92
     spree
    0.91
    oise
    0.87
     attackers
    0.86
    attacks
    0.86
    ocalypse
    0.83
    CVE
    0.81
    Activations Density 0.031%

    No Known Activations