© 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. 8-RES-JB
    11. 3241
    Prev
    Next
    INDEX
    Explanations

    links to shareable stories or articles

    oai_token-act-pair · gpt-3.5-turbo

    references to sharing or engaging with content

    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
    bats
    -0.84
    Ĭ±
    -0.68
    Band
    -0.67
    Īè
    -0.67
     showers
    -0.63
    ãĥīãĥ©
    -0.62
    »Ĵ
    -0.61
    ±
    -0.61
    aus
    -0.60
    resp
    -0.58
    POSITIVE LOGITS
     ARTICLE
    1.01
     article
    0.96
     month
    0.80
     week
    0.77
     year
    0.73
     disclaimer
    0.72
    iannopoulos
    0.72
     guiActiveUn
    0.70
     page
    0.70
     slideshow
    0.69
    Activations Density 0.046%

    No Known Activations