© 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. 9-RES-JB
    11. 22748
    Prev
    Next
    INDEX
    Explanations

    specific phrases indicating an additional detail or topic in a discussion

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate additional information or supplementary details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pire
    -0.86
    terday
    -0.84
    soType
    -0.79
    rely
    -0.74
    fell
    -0.73
    Spread
    -0.72
    é¾įåĸļ士
    -0.71
    ãģ¦
    -0.70
    mint
    -0.70
    ãĤ¢ãĥ«
    -0.70
    POSITIVE LOGITS
     usual
    1.49
     obvious
    1.41
     aforementioned
    1.24
     obligatory
    1.17
     basics
    1.17
     occasional
    1.16
     mundane
    1.06
     immediate
    1.04
     fact
    1.00
     requisite
    0.93
    Activations Density 0.203%

    No Known Activations