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

    Neuronpedia

    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. 21794
    Prev
    Next
    INDEX
    Explanations

    comparisons of quantities using "than"

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases indicating differences in quantity or quality

    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
    ISSION
    -0.73
    ointed
    -0.71
    olitan
    -0.70
    resa
    -0.70
    oint
    -0.70
    ALE
    -0.68
    Leaks
    -0.68
    nton
    -0.65
    Winged
    -0.65
    iol
    -0.65
    POSITIVE LOGITS
     usual
    1.07
     typical
    0.92
     previous
    0.85
     conventional
    0.83
     ours
    0.82
     traditional
    0.81
    usual
    0.81
     comparable
    0.80
     normal
    0.78
     ordinary
    0.74
    Activations Density 0.150%

    No Known Activations