© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 3309
    Prev
    Next
    INDEX
    Explanations

    mentions of tragic events and condolences

    oai_token-act-pair · gpt-3.5-turbo

    mentions of death and expressions of grief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    direction
    -0.76
    ivalry
    -0.73
    Style
    -0.72
     mode
    -0.71
    irection
    -0.68
    iquette
    -0.68
    mosp
    -0.67
    wcsstore
    -0.66
     familiarity
    -0.65
     explanations
    -0.64
    POSITIVE LOGITS
     murdered
    0.99
     slain
    0.96
     deceased
    0.94
     killed
    0.94
     drowned
    0.91
     abducted
    0.91
     martyr
    0.90
     gunned
    0.88
     detainee
    0.88
     kidnapped
    0.86
    Activations Density 0.352%

    No Known Activations