© 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 EvalsExportsinterp-engineNEWAPI 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. 1272
    Prev
    Next
    INDEX
    Explanations

    sentence structure patterns related to speaking or reporting

    oai_token-act-pair · gpt-3.5-turbo

    emphatic expressions and statements

    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
     Lyme
    -0.66
     NES
    -0.60
     Subject
    -0.56
     Atk
    -0.56
     Hutchinson
    -0.56
     VM
    -0.55
     Vita
    -0.55
     Plant
    -0.54
     Ranch
    -0.54
     DIY
    -0.54
    POSITIVE LOGITS
    etheless
    1.05
    theless
    0.98
    ulty
    0.95
    mosp
    0.94
    zbollah
    0.93
    govtrack
    0.87
    ngth
    0.85
    icularly
    0.84
    */(
    0.84
    etheus
    0.83
    Activations Density 0.272%

    No Known Activations