© 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. 10853
    Prev
    Next
    INDEX
    Explanations

    words related to the beginning or starting of an action or process

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "begin" and its variations

    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
    allo
    -0.72
    outer
    -0.68
    ndra
    -0.68
    arse
    -0.67
    oted
    -0.67
    atti
    -0.67
    aths
    -0.66
    rats
    -0.65
    olded
    -0.65
    anda
    -0.63
    POSITIVE LOGITS
     anew
    1.21
     circulating
    0.84
    ŃĶ
    0.78
     hostilities
    0.78
     "$:/
    0.77
    nings
    0.76
     preparations
    0.75
    WithNo
    0.73
     trending
    0.72
    quire
    0.71
    Activations Density 0.047%

    No Known Activations