© 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. 16224
    Prev
    Next
    INDEX
    Explanations

    words related to extreme cold or severe weather conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to cold temperatures and species associated with cold environments

    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
    holder
    -0.73
     Controls
    -0.71
    OVER
    -0.71
    Guide
    -0.70
     Classification
    -0.68
    Translation
    -0.67
    Split
    -0.66
     Genetics
    -0.66
     Pharmaceutical
    -0.65
     Steps
    -0.64
    POSITIVE LOGITS
     frig
    1.01
    ging
    0.96
    atures
    0.92
    terness
    0.89
    acies
    0.88
    bly
    0.87
    ignt
    0.86
    glers
    0.85
    itial
    0.85
    idity
    0.83
    Activations Density 0.007%

    No Known Activations