© 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. 8-RES-JB
    11. 7831
    Prev
    Next
    INDEX
    Explanations

    the conjunction "As" at the start of a sentence

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "As."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osc
    -0.61
    ||||
    -0.61
    ãģ®å®
    -0.58
     Ùħ
    -0.56
    Ùĩ
    -0.56
    scope
    -0.55
    roads
    -0.55
     whatsoever
    -0.54
    ãģł
    -0.54
    neg
    -0.54
    POSITIVE LOGITS
    bestos
    1.43
    semb
    1.39
    piring
    1.35
    phalt
    1.29
    pects
    1.25
    ylum
    1.24
    semble
    1.18
    king
    1.16
    ymm
    1.14
    piration
    1.13
    Activations Density 0.088%

    No Known Activations