© 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. 6-RES-JB
    11. 17634
    Prev
    Next
    INDEX
    Explanations

    movie-related content such as movie titles, locations, and genres

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utive
    -0.69
    umen
    -0.67
    reth
    -0.62
    atively
    -0.62
    uto
    -0.61
    UF
    -0.60
    jured
    -0.59
    ¬¼
    -0.58
    ason
    -0.57
    iple
    -0.57
    POSITIVE LOGITS
     lest
    1.02
     albeit
    0.94
     wherein
    0.94
     aka
    0.92
     huh
    0.91
     namely
    0.88
     haha
    0.87
     eh
    0.86
     which
    0.85
     circa
    0.83
    Activations Density 0.719%

    No Known Activations