© 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 EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 3975
    Prev
    Next
    INDEX
    Explanations

    references to specific daily news publications

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to specific publications or news organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    cence
    -0.75
    nesota
    -0.74
    ĺħ
    -0.73
    regon
    -0.70
    raped
    -0.67
    lov
    -0.67
    ery
    -0.66
    omnia
    -0.66
    rity
    -0.66
    rule
    -0.64
    POSITIVE LOGITS
     News
    1.02
    News
    0.71
    geist
    0.70
     news
    0.61
    Journal
    0.59
     Chronicle
    0.59
     NEWS
    0.59
     Prophet
    0.58
    OLOG
    0.57
     Observer
    0.56
    Activations Density 0.170%

    No Known Activations