© 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. 10-RES-JB
    11. 1445
    Prev
    Next
    INDEX
    Explanations

    words with the prefix "pre-"

    oai_token-act-pair · gpt-3.5-turbo

    words or terms that start with "pre-" indicating a sense of prior action or preparation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GOODMAN
    -0.83
    loo
    -0.67
     laughter
    -0.66
    ourcing
    -0.65
    adia
    -0.64
    ãĥīãĥ©ãĤ´ãĥ³
    -0.63
     dots
    -0.61
    IBLE
    -0.61
    è¦ļéĨĴ
    -0.60
    ãĤ¼ãĤ¦ãĤ¹
    -0.57
    POSITIVE LOGITS
    cision
    1.47
    cious
    1.44
    pared
    1.43
    cise
    1.37
    requisite
    1.33
    requisites
    1.33
    ferred
    1.28
    empt
    1.26
    ference
    1.22
    historic
    1.20
    Activations Density 0.018%

    No Known Activations