© 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. 11-RES-JB
    11. 20418
    Prev
    Next
    INDEX
    Explanations

    dates and specific years mentioned in various studies and reports

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific reports and studies along with their publication dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atives
    -0.88
    osponsors
    -0.87
     idols
    -0.83
    artifacts
    -0.81
    Tags
    -0.81
    packs
    -0.80
    devices
    -0.80
    killers
    -0.77
     sauces
    -0.77
    obiles
    -0.76
    POSITIVE LOGITS
     article
    1.25
     report
    1.20
     study
    1.18
     interview
    1.17
     survey
    1.15
     review
    1.08
     analysis
    1.08
     essay
    1.08
     audit
    1.08
     Gallup
    1.08
    Activations Density 0.093%

    No Known Activations