© 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. 24193
    Prev
    Next
    INDEX
    Explanations

    adjectives conveying strong emotions or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    intensifiers and modifiers describing degrees of quality or experience

    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
    nown
    -0.64
    existence
    -0.62
    amiya
    -0.61
    ilial
    -0.60
     corrid
    -0.58
    abiding
    -0.56
    erness
    -0.54
     Archives
    -0.54
     Neurolog
    -0.54
    antle
    -0.53
    POSITIVE LOGITS
     traction
    1.00
     mileage
    0.96
     foothold
    0.85
    IFIED
    0.80
     bang
    0.77
     lucky
    0.74
     footing
    0.71
     attention
    0.68
    imentary
    0.68
     notoriety
    0.68
    Activations Density 0.229%

    No Known Activations