© 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. 22268
    Prev
    Next
    INDEX
    Explanations

    specific events, organizations, and locations

    oai_token-act-pair · gpt-3.5-turbo

    entities and concepts related to historical and political contexts

    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
    ,,,,
    -0.88
    rupulous
    -0.74
    etheless
    -0.74
    gans
    -0.71
    ,,,,,,,,
    -0.70
    iets
    -0.70
     Originally
    -0.67
    AppData
    -0.66
     cannabin
    -0.66
     Luxem
    -0.63
    POSITIVE LOGITS
     outing
    1.05
     session
    1.03
     takeover
    1.00
    bernatorial
    1.00
     showdown
    0.96
     uprising
    0.96
     onslaught
    0.95
     trials
    0.93
     rollout
    0.93
     trial
    0.91
    Activations Density 0.659%

    No Known Activations