© 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. 23566
    Prev
    Next
    INDEX
    Explanations

    the phrase "start off" or "starts off."

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the beginning or initiation of actions or events

    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
     CrossRef
    -0.74
     grandchildren
    -0.67
    soDeliveryDate
    -0.61
    ged
    -0.61
     extensions
    -0.61
     dearly
    -0.61
     cats
    -0.60
     backdrop
    -0.60
     descendants
    -0.60
     encyclopedia
    -0.59
    POSITIVE LOGITS
    weak
    0.76
    WithNo
    0.74
    ©¶æ¥µ
    0.73
    imester
    0.71
    steen
    0.71
    odox
    0.68
    ru
    0.68
     anew
    0.68
    ¼
    0.67
     hes
    0.66
    Activations Density 0.050%

    No Known Activations