© 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. 11-RES-JB
    11. 20564
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers and characters

    oai_token-act-pair · gpt-3.5-turbo

    alphanumeric sequences and file types, particularly those resembling data or code formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Orderable
    -0.74
     newsp
    -0.73
     Rising
    -0.70
     Rampage
    -0.70
     Schr
    -0.70
     metic
    -0.63
     glim
    -0.63
     Rik
    -0.62
     inflamm
    -0.61
     Kos
    -0.61
    POSITIVE LOGITS
    bda
    1.37
    bd
    1.34
    eda
    1.34
    da
    1.33
    cb
    1.32
    ba
    1.31
    efe
    1.30
    cf
    1.29
    bf
    1.28
    ef
    1.28
    Activations Density 0.040%

    No Known Activations