© 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. 3302
    Prev
    Next
    INDEX
    Explanations

    dollar amounts or numbers

    oai_token-act-pair · gpt-3.5-turbo

    commas and other punctuation in numerical or financial contexts

    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
    ²¾
    -0.77
    irie
    -0.68
    icial
    -0.68
    ¤
    -0.67
    ESE
    -0.66
    ARCH
    -0.66
    ļéĨĴ
    -0.63
    nesota
    -0.61
     è£ıè
    -0.59
    iral
    -0.58
    POSITIVE LOGITS
    000
    1.06
     whereas
    0.98
     according
    0.95
    Downloadha
    0.93
     respectively
    0.91
     implying
    0.90
     compared
    0.90
    maximum
    0.87
    depending
    0.85
     excluding
    0.84
    Activations Density 0.197%

    No Known Activations