© 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. 9-RES-JB
    11. 15745
    Prev
    Next
    INDEX
    Explanations

    phrases related to matters of policy and international relations

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases that suggest addition or connection between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    meric
    -0.77
    kees
    -0.77
    ãĥĥãĤ¯
    -0.74
    ãĥ¯ãĥ³
    -0.71
    usha
    -0.68
    oeuv
    -0.66
     Eat
    -0.65
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.63
    ãĤ©
    -0.63
    ãģĨ
    -0.62
    POSITIVE LOGITS
     consequently
    1.02
     especially
    0.94
     elsewhere
    0.93
     hence
    0.93
     indeed
    0.90
     wider
    0.86
     certainly
    0.86
     particularly
    0.85
     consequ
    0.83
     possibly
    0.82
    Activations Density 0.319%

    No Known Activations