© 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. 15016
    Prev
    Next
    INDEX
    Explanations

    quotes or reported speech

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve quotations or statements made by individuals or entities

    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
    ļéĨĴ
    -0.87
    ²¾
    -0.80
    ĻĤ
    -0.77
    Widget
    -0.76
    ¬¼
    -0.75
    ħĭ
    -0.72
    ãĤ©
    -0.71
    ldom
    -0.70
    ´
    -0.69
    phant
    -0.69
    POSITIVE LOGITS
     wrote
    1.53
     reads
    1.49
     writes
    1.28
     said
    1.25
     commented
    1.18
     according
    1.15
     stated
    1.12
     read
    1.10
     explained
    1.09
     says
    1.08
    Activations Density 0.090%

    No Known Activations