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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 17297
    Prev
    Next
    INDEX
    Explanations

    verbs relating to giving advice or making suggestions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "suggest" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tesy
    -0.74
    ILA
    -0.74
    respective
    -0.73
    gie
    -0.73
    ãĥ¼ãĥ
    -0.71
    brance
    -0.70
    stood
    -0.69
    displayText
    -0.69
    ceans
    -0.68
    cedented
    -0.68
    POSITIVE LOGITS
     lowering
    0.94
     abandoning
    0.93
     that
    0.92
     alternatives
    0.92
     eliminating
    0.91
     removing
    0.88
     abol
    0.88
     replacing
    0.88
     contacting
    0.87
     modifying
    0.87
    Activations Density 0.091%

    No Known Activations