© 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. 4690
    Prev
    Next
    INDEX
    Explanations

    mentions of specific companies, financial terms, and contract details

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

    comments related to news articles or editorial content

    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
     ferment
    -0.72
     constrained
    -0.70
     bind
    -0.70
     blush
    -0.70
     wrench
    -0.69
     recol
    -0.68
     jumper
    -0.68
     phase
    -0.67
     slit
    -0.67
     chopping
    -0.66
    POSITIVE LOGITS
    com
    1.46
    Org
    1.43
    COM
    1.35
    Com
    1.32
    Ru
    1.31
    Net
    1.25
    TV
    1.18
    org
    1.16
    IO
    1.15
    tv
    1.14
    Activations Density 0.072%

    No Known Activations