© 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. 13589
    Prev
    Next
    INDEX
    Explanations

    events involving physical impact or collision

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of impactful physical events or actions

    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
    Gene
    -0.75
     Kyoto
    -0.69
    actionDate
    -0.69
     Institutes
    -0.67
     festivals
    -0.67
     Behavioral
    -0.66
    izu
    -0.66
     specialization
    -0.66
    cia
    -0.65
     Serie
    -0.64
    POSITIVE LOGITS
     toppled
    1.30
     topp
    1.22
     tumble
    1.18
     overturned
    1.18
     topple
    1.15
     debris
    1.14
     bould
    1.14
     crashing
    1.14
     disl
    1.12
     dangling
    1.11
    Activations Density 0.334%

    No Known Activations