© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 17527
    Prev
    Next
    INDEX
    Explanations

    words related to animals

    oai_token-act-pair · gpt-3.5-turbo

    words with specific phonetic qualities or structures, particularly those that convey emotional or descriptive nuances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.83
    isal
    -0.77
    ITY
    -0.76
    jen
    -0.73
    IFE
    -0.71
    enthal
    -0.70
    olis
    -0.70
    eness
    -0.69
    NK
    -0.68
    icity
    -0.68
    POSITIVE LOGITS
     eyed
    0.87
     pot
    0.85
     clad
    0.77
     poetic
    0.75
     fide
    0.73
     pig
    0.71
     pots
    0.69
     lyr
    0.69
     sum
    0.67
     nostalgic
    0.67
    Activations Density 0.186%

    No Known Activations