© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4212
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to politics and economics

    oai_token-act-pair · gpt-3.5-turbo

    key figures and events related to political and social dynamics

    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
     ACTIONS
    -0.66
     convened
    -0.64
     Tribe
    -0.62
     conflic
    -0.57
    âĶĢâĶĢâĶĢâĶĢ
    -0.56
    anical
    -0.56
     Vance
    -0.54
     Turk
    -0.53
    asonable
    -0.53
    vironments
    -0.51
    POSITIVE LOGITS
    Shell
    0.61
    Virgin
    0.57
    vernight
    0.56
    rawdownloadcloneembedreportprint
    0.56
    layer
    0.52
     Metatron
    0.52
     bombers
    0.51
     brakes
    0.51
     ITV
    0.51
    breaker
    0.51
    Activations Density 1.401%

    No Known Activations