© 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. 6-RES-JB
    11. 23717
    Prev
    Next
    INDEX
    Explanations

    URLs within a text

    oai_token-act-pair · gpt-3.5-turbo

    content related to stories and news articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    veland
    -0.89
    amina
    -0.80
    emouth
    -0.78
    apons
    -0.76
    xit
    -0.76
    untarily
    -0.75
    chy
    -0.74
    assi
    -0.74
    ornia
    -0.73
    untled
    -0.73
    POSITIVE LOGITS
     unfolding
    0.99
     narrated
    0.91
     Narr
    0.86
     poems
    0.85
     fiction
    0.81
     Hemp
    0.79
     novels
    0.79
     unfold
    0.78
     prol
    0.77
     rewritten
    0.77
    Activations Density 0.419%

    No Known Activations