© 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. 187
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "have," typically indicating possession or requirement

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "have" in various contexts

    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
    stre
    -0.73
    ilation
    -0.71
     humili
    -0.61
    andan
    -0.59
    Introdu
    -0.57
     Slowly
    -0.57
    odge
    -0.56
     Initially
    -0.56
    attery
    -0.55
     neigh
    -0.55
    POSITIVE LOGITS
     recourse
    0.95
     enough
    0.91
    stood
    0.90
     permission
    0.90
     anymore
    0.86
     sufficient
    0.85
     access
    0.83
     jurisdiction
    0.79
    standing
    0.77
     sympathy
    0.75
    Activations Density 0.095%

    No Known Activations