© 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. 6350
    Prev
    Next
    INDEX
    Explanations

    information related to legal cases and interventions

    oai_token-act-pair · gpt-3.5-turbo

    sentences that relate to political or social statements and events

    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
     democrat
    -0.86
    kefeller
    -0.75
     tremend
    -0.70
     disson
    -0.68
     dimensional
    -0.66
     scouting
    -0.65
     insur
    -0.65
     exciting
    -0.65
     unequ
    -0.65
     imaginable
    -0.65
    POSITIVE LOGITS
     Asked
    1.08
     Others
    1.07
     Later
    1.01
     However
    1.01
     Earlier
    1.01
     Initially
    1.01
     Previously
    1.00
     Officials
    1.00
     Instead
    0.99
     Though
    0.96
    Activations Density 0.624%

    No Known Activations