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

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 23977
    Prev
    Next
    INDEX
    Explanations

    Swedish words or text containing the letter "å"

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific character or symbol repeated multiple times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iazep
    -0.76
    idepress
    -0.76
    puted
    -0.76
    aimon
    -0.72
    agonist
    -0.71
    iple
    -0.68
    Uncommon
    -0.67
    icity
    -0.66
    PLIED
    -0.65
     overdoses
    -0.64
    POSITIVE LOGITS
    å
    0.85
    ĺ
    0.82
    rd
    0.81
    gaard
    0.79
    «
    0.78
    ø
    0.77
    sb
    0.76
    sson
    0.73
    µ
    0.73
    Ļ
    0.72
    Activations Density 0.025%

    No Known Activations