© 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. 4008
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions and descriptions of intense physical suffering

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

    descriptors of intense emotions or physical sensations

    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
     Assist
    -0.76
    workshop
    -0.70
     Dock
    -0.68
     Prospect
    -0.66
     Concert
    -0.66
     Tourism
    -0.66
     Equity
    -0.65
     Holiday
    -0.65
     Activities
    -0.64
     Gutenberg
    -0.64
    POSITIVE LOGITS
     throb
    1.10
     claws
    1.05
     venom
    1.01
     marrow
    0.99
     clen
    0.99
     burns
    0.98
     corro
    0.97
     teeth
    0.96
     fury
    0.96
    terness
    0.95
    Activations Density 0.646%

    No Known Activations