© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7588
    Prev
    Next
    INDEX
    Explanations

    instances of vulnerability or susceptibility

    oai_token-act-pair · gpt-3.5-turbo

    the concept of vulnerability in various contexts and populations

    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
    zos
    -0.77
    OVA
    -0.76
    OTO
    -0.72
    tein
    -0.71
    omer
    -0.68
     Chemistry
    -0.67
    OPA
    -0.66
    omers
    -0.66
     Kinnikuman
    -0.66
    row
    -0.65
    POSITIVE LOGITS
     vulnerable
    1.39
    ulnerable
    1.27
     vulner
    1.20
     adolesc
    1.04
     susceptible
    0.95
     victims
    0.92
     unsuspecting
    0.89
     vulnerability
    0.88
     vulnerabilities
    0.86
     metic
    0.81
    Activations Density 0.009%

    No Known Activations