© 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. 20402
    Prev
    Next
    INDEX
    Explanations

    news-related information or updates

    oai_token-act-pair · gpt-3.5-turbo

    references to hostage situations and related incidents

    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
    utenberg
    -0.82
    ¢
    -0.79
    metics
    -0.78
    é¾
    -0.76
    TPPStreamerBot
    -0.75
    dust
    -0.74
    STD
    -0.74
    geist
    -0.74
    ãĤ§
    -0.73
    iard
    -0.73
    POSITIVE LOGITS
     hostages
    1.95
     ransom
    1.95
     captives
    1.86
     hostage
    1.84
     captivity
    1.83
     kidn
    1.80
     kidnapped
    1.72
     kidnap
    1.61
     abduct
    1.60
     abducted
    1.58
    Activations Density 0.333%

    No Known Activations