© 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. 7-RES-JB
    11. 12649
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating obligation or necessity

    oai_token-act-pair · gpt-3.5-turbo

    the word "ought" in various contexts related to obligations or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Puzzle
    -0.61
    Arab
    -0.61
    ching
    -0.60
     Polo
    -0.59
    д
    -0.59
    ula
    -0.58
    KY
    -0.58
    fal
    -0.57
     Christensen
    -0.57
    ãĥĩãĤ£
    -0.57
    POSITIVE LOGITS
    lessly
    0.84
     ideally
    0.82
    ratulations
    0.81
    arna
    0.77
    ILY
    0.73
    entimes
    0.73
     rightfully
    0.72
    reprene
    0.71
    ily
    0.71
     disclaim
    0.70
    Activations Density 0.009%

    No Known Activations