© 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. 4444
    Prev
    Next
    INDEX
    Explanations

    information related to accidents and emergencies like crashes, evacuations, casualties, and rescue operations

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

    information regarding incidents or disasters

    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
    Ô
    -0.80
    HCR
    -0.78
    CLASSIFIED
    -0.71
    andowski
    -0.71
    ħĭ
    -0.71
    isoft
    -0.67
    izon
    -0.66
    Beh
    -0.66
     NOTICE
    -0.65
     Turing
    -0.65
    POSITIVE LOGITS
     wreckage
    1.25
     debris
    1.18
     collapsed
    1.18
     rubble
    1.10
     collapses
    1.09
     flames
    1.07
     landslide
    1.06
     firefighters
    1.06
     collapse
    1.06
     landsl
    1.05
    Activations Density 0.446%

    No Known Activations