© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8-RES-JB
    11. 14378
    Prev
    Next
    INDEX
    Explanations

    references to polar-related terms, such as "polar opposite" or "polar bear"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "polar" and its variations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    bler
    -0.83
    LER
    -0.76
    lished
    -0.75
    CHA
    -0.74
    ptroller
    -0.73
    rahim
    -0.73
    dump
    -0.70
    alach
    -0.70
    BACK
    -0.68
    ECH
    -0.67
    POSITIVE LOGITS
    izing
    1.10
     vortex
    1.04
     oppos
    1.04
    ities
    0.98
    ising
    0.98
    oid
    0.90
     extremes
    0.89
    ized
    0.88
    ised
    0.87
    imeter
    0.86
    Activations Density 0.033%

    No Known Activations