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

    Neuronpedia

    Jacobian LensNEW
    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. 4870
    Prev
    Next
    INDEX
    Explanations

    words related to significant negative events or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to severe negative events or consequences

    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
    etch
    -0.77
    pel
    -0.76
    guyen
    -0.76
    atum
    -0.75
    verbs
    -0.74
    bors
    -0.74
    cling
    -0.74
    ymph
    -0.73
    appa
    -0.72
    uni
    -0.69
    POSITIVE LOGITS
    itous
    1.15
     havoc
    0.97
     consequences
    0.89
     catastrophic
    0.86
     impacts
    0.76
     catast
    0.76
    ity
    0.76
     catastrophe
    0.75
     inev
    0.74
     endanger
    0.72
    Activations Density 0.017%

    No Known Activations