© 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. 3-RES-JB
    11. 1559
    Prev
    Next
    INDEX
    Explanations

    words related to vulnerabilities or weaknesses

    oai_token-act-pair · gpt-3.5-turbo

    references to weaknesses in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agher
    -0.92
    rea
    -0.84
    ateur
    -0.74
    aston
    -0.71
    ahon
    -0.71
    iser
    -0.70
    aughlin
    -0.68
    zos
    -0.68
    ilon
    -0.68
    alogue
    -0.67
    POSITIVE LOGITS
     weakness
    1.04
     weaknesses
    0.87
     aversion
    0.85
     limitation
    0.83
     weaken
    0.81
    nesses
    0.81
     weakening
    0.80
     vulner
    0.79
     Weak
    0.78
    Weak
    0.77
    Activations Density 0.009%

    No Known Activations