© 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. 2815
    Prev
    Next
    INDEX
    Explanations

    phrases related to witnessing events or actions

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

    instances related to eyewitness accounts and witness testimonies in incidents

    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
    retty
    -0.81
    Quantity
    -0.78
    isite
    -0.73
    Orig
    -0.72
    actionDate
    -0.69
    Creat
    -0.68
    edIn
    -0.66
    hibition
    -0.66
     undermin
    -0.65
    btn
    -0.65
    POSITIVE LOGITS
     witnessed
    1.21
     rushed
    1.14
     testified
    1.13
     yelled
    1.13
     awoke
    1.11
     heard
    1.11
     alerted
    1.09
     described
    1.09
     remembers
    1.08
     recounted
    1.07
    Activations Density 0.325%

    No Known Activations