© 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. 4-RES-JB
    11. 19839
    Prev
    Next
    INDEX
    Explanations

    references to the word "au" followed by a specific number

    oai_token-act-pair · gpt-3.5-turbo

    references to "au" in various contexts, likely indicating a focus on a specific group or subject related to that term

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

    No Comments

    Negative Logits
    behind
    -0.80
    ONES
    -0.78
    Ö¼
    -0.75
    çīĪ
    -0.71
    ij士
    -0.69
    enegger
    -0.67
    locks
    -0.67
    tics
    -0.64
    âķIJ
    -0.63
    tons
    -0.63
    POSITIVE LOGITS
     au
    0.93
    atha
    0.84
     veter
    0.81
    clair
    0.79
    vier
    0.78
    ught
    0.78
    ghan
    0.77
    quer
    0.73
    qua
    0.72
    zac
    0.72
    Activations Density 0.012%

    No Known Activations