© 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. 12-RES-JB
    11. 3089
    Prev
    Next
    INDEX
    Explanations

    references to tragic or dangerous situations/events, such as suicide or accidents

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to suicide and discussions surrounding it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    worn
    -0.65
     nerves
    -0.62
     times
    -0.60
     union
    -0.59
     Hammer
    -0.59
     Union
    -0.57
     Abram
    -0.56
     Authority
    -0.55
     halves
    -0.55
     kicking
    -0.55
    POSITIVE LOGITS
    itable
    1.33
    zanne
    1.30
    perm
    1.26
    icide
    1.23
    arez
    1.19
    icides
    1.19
    icidal
    1.16
    cc
    1.15
    itably
    1.14
    ited
    1.12
    Activations Density 0.016%

    No Known Activations