© 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. 8-RES-JB
    11. 19294
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a degree of intensity or comparison

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a degree of messiness or complexity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rats
    -0.84
    reys
    -0.81
    ħĭ
    -0.80
    metics
    -0.77
    pects
    -0.76
    rates
    -0.76
    uers
    -0.75
    oons
    -0.74
    ards
    -0.74
    atars
    -0.74
    POSITIVE LOGITS
     luck
    1.01
     overlap
    0.85
     extra
    0.76
     mischief
    0.74
     trouble
    0.73
     elbow
    0.73
    angu
    0.72
     irony
    0.72
     misinformation
    0.71
     realism
    0.71
    Activations Density 0.044%

    No Known Activations