© 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. 5190
    Prev
    Next
    INDEX
    Explanations

    mentions of the Islamic State (IS) terrorist group

    oai_token-act-pair · gpt-3.5-turbo
    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
     Trace
    -0.72
     Ame
    -0.66
     Sue
    -0.66
    ilight
    -0.65
    atically
    -0.62
    ographics
    -0.61
    iors
    -0.59
     tape
    -0.59
    alties
    -0.57
    ouses
    -0.57
    POSITIVE LOGITS
    DN
    1.15
    AF
    1.14
    IL
    1.11
    BN
    1.11
    IK
    1.09
    RO
    1.08
    Vs
    1.08
    FP
    1.08
    DS
    1.06
    CEPT
    1.05
    Activations Density 0.038%

    No Known Activations