© 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. 6268
    Prev
    Next
    INDEX
    Explanations

    terms related to governmental and intelligence agencies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to intelligence, policies, and legal matters

    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
    姫
    -0.77
    Jr
    -0.72
    mallow
    -0.69
    é¾įåĸļ士
    -0.67
    mite
    -0.67
    urnal
    -0.65
    otropic
    -0.64
    ecast
    -0.64
    Maps
    -0.64
    lake
    -0.61
    POSITIVE LOGITS
    afety
    0.67
     Directive
    0.65
    indust
    0.65
    backs
    0.64
    hers
    0.63
    rics
    0.61
    arations
    0.61
    riage
    0.60
    iries
    0.60
    ccess
    0.59
    Activations Density 0.579%

    No Known Activations