© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 21370
    Prev
    Next
    INDEX
    Explanations

    various gibberish words and names with different accents and characters

    oai_token-act-pair · gpt-3.5-turbo

    repeated characters or patterns in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    galitarian
    -0.65
     Marlins
    -0.62
     MacArthur
    -0.58
     containment
    -0.57
    ced
    -0.55
    FUL
    -0.54
     Wynne
    -0.53
     Mayhem
    -0.53
     Shelby
    -0.53
    cess
    -0.53
    POSITIVE LOGITS
    ournal
    1.04
    utsu
    0.97
    ani
    0.94
    ulia
    0.93
    ean
    0.91
    unction
    0.89
    oint
    0.88
    eva
    0.87
    ataka
    0.87
    odi
    0.87
    Activations Density 0.046%

    No Known Activations