© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 910
    Prev
    Next
    INDEX
    Explanations

    vulnerability and susceptibility to various risks or threats

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases indicating susceptibility or weakness to various threats or dangers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zos
    -0.77
    fare
    -0.71
    inth
    -0.70
    ALSE
    -0.70
    corn
    -0.69
    furt
    -0.64
    owler
    -0.64
    gall
    -0.62
    zzi
    -0.60
    owed
    -0.60
    POSITIVE LOGITS
     vulnerable
    0.91
     vulnerability
    0.76
     embr
    0.73
     habitat
    0.71
    itiz
    0.70
     vulnerabilities
    0.70
     vulner
    0.69
     susceptible
    0.69
    ivities
    0.68
     environment
    0.68
    Activations Density 0.053%

    No Known Activations