© 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. 0-RES-JB
    11. 2331
    Prev
    Next
    INDEX
    Explanations

    a specific pattern of characters, possibly indicating an error, as it doesn't seem to have a coherent interpretation in the context of the other neurons' behaviors

    oai_token-act-pair · gpt-3.5-turbo

    special characters or unusual symbols within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DC
    -0.76
     Death
    -0.72
     Penn
    -0.68
     Hob
    -0.68
     Faw
    -0.65
     Adams
    -0.65
     census
    -0.65
     Keystone
    -0.64
     sage
    -0.64
    ranch
    -0.63
    POSITIVE LOGITS
    ë
    3.74
    ì
    3.42
    ê
    3.41
    í
    3.34
    ìĿ
    3.28
     ë
    2.93
    íķ
    2.81
     ì
    2.77
    ëĭ
    2.70
    ã
    1.83
    Activations Density 0.014%

    No Known Activations