© 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. 3228
    Prev
    Next
    INDEX
    Explanations

    reports of news events

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

    mentions of various news reports and media coverage

    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
    chest
    -0.67
    forestation
    -0.61
    allery
    -0.59
    ses
    -0.59
    tons
    -0.56
    avery
    -0.56
    viation
    -0.56
     welf
    -0.56
    Textures
    -0.56
    oka
    -0.55
    POSITIVE LOGITS
     quoting
    1.04
     surfaced
    1.00
     circulating
    0.96
     citing
    0.89
     alleging
    0.87
     circulated
    0.85
     originating
    0.81
    age
    0.80
     claiming
    0.80
     emanating
    0.79
    Activations Density 0.104%

    No Known Activations