© 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. 2-RES-JB
    11. 22546
    Prev
    Next
    INDEX
    Explanations

    the word "rose" and derivatives thereof

    oai_token-act-pair · gpt-3.5-turbo

    words related to various types of "rose" and escalating tensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disparate
    -0.72
    ointed
    -0.71
    ounced
    -0.69
     DAM
    -0.69
     HIP
    -0.67
    netic
    -0.65
    ãĥīãĥ©
    -0.63
    Copyright
    -0.62
     paycheck
    -0.62
    urated
    -0.61
    POSITIVE LOGITS
    xual
    1.63
    rose
    1.17
    mere
    0.92
    phrine
    0.91
    DragonMagazine
    0.87
    escal
    0.86
    tto
    0.86
    terday
    0.85
    erie
    0.81
    velt
    0.80
    Activations Density 0.010%

    No Known Activations