© 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. 17700
    Prev
    Next
    INDEX
    Explanations

    references to espionage or spies

    oai_token-act-pair · gpt-3.5-turbo

    references to espionage or spying

    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
    xual
    -0.96
    esville
    -0.75
    à¼
    -0.73
    clus
    -0.71
    jiang
    -0.67
    ĸļ
    -0.66
    kell
    -0.64
    Interstitial
    -0.64
    mia
    -0.64
     Explain
    -0.64
    POSITIVE LOGITS
    glass
    1.02
    oleon
    0.93
    sonian
    0.90
    ware
    0.84
    dropping
    0.81
     satellites
    0.79
    OSH
    0.78
    plane
    0.76
    doms
    0.75
     spying
    0.73
    Activations Density 0.038%

    No Known Activations