© 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. 5355
    Prev
    Next
    INDEX
    Explanations

    numbers preceded by a space and followed by non-alphabetic characters

    oai_token-act-pair · gpt-3.5-turbo

    references to the number 58 in varying contexts

    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
    •Embedding Space Digit Features

    No Comments

    Negative Logits
    itan
    -0.78
     ART
    -0.76
     Pandora
    -0.72
    Cart
    -0.71
     Bend
    -0.70
     Bowman
    -0.69
     Asgard
    -0.69
     cart
    -0.69
    oton
    -0.68
     fruits
    -0.68
    POSITIVE LOGITS
     68
    1.66
     98
    1.64
     58
    1.64
     88
    1.48
     178
    1.47
     118
    1.46
     78
    1.45
    58
    1.44
     138
    1.44
    118
    1.44
    Activations Density 0.073%

    No Known Activations