© 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. 3-RES-JB
    11. 3193
    Prev
    Next
    INDEX
    Explanations

    words related to software development and updates

    oai_token-act-pair · gpt-3.5-turbo

    terms related to project management and development processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Socialist
    -0.85
    heat
    -0.82
     Stalin
    -0.71
     socialist
    -0.71
     Muss
    -0.70
    Liber
    -0.67
     roadside
    -0.66
    indu
    -0.66
     Subst
    -0.66
     Democrat
    -0.66
    POSITIVE LOGITS
     devs
    1.14
    catentry
    0.98
     testers
    0.97
     developers
    0.95
     Developers
    0.93
     SDK
    0.93
     roadmap
    0.93
     feedback
    0.91
     announcements
    0.90
     milestones
    0.88
    Activations Density 1.053%

    No Known Activations