© 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. 2-RES-JB
    11. 17491
    Prev
    Next
    INDEX
    Explanations

    words related to blurriness or blending

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and related forms of verbs that indicate ongoing actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BIL
    -0.72
     kindred
    -0.66
     Centers
    -0.66
    PRES
    -0.63
    Recomm
    -0.63
    è¦ļéĨĴ
    -0.63
    =-=-=-=-
    -0.62
    »Ĵ
    -0.61
    éŃĶ
    -0.61
    æ©Ł
    -0.61
    POSITIVE LOGITS
    ulence
    0.79
    hemy
    0.79
    imaru
    0.75
    otide
    0.75
    imore
    0.73
    beard
    0.68
    ace
    0.68
     soap
    0.68
     Faction
    0.67
    etooth
    0.67
    Activations Density 0.075%

    No Known Activations