© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9037
    Prev
    Next
    INDEX
    Explanations

    Chinese words or characters

    oai_token-act-pair · gpt-3.5-turbo

    specific special characters or symbols in text

    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
    ufact
    -0.92
    eger
    -0.72
    phia
    -0.69
    doms
    -0.68
    eah
    -0.65
     goats
    -0.65
    ourt
    -0.64
    imore
    -0.64
    sembly
    -0.63
    ensical
    -0.61
    POSITIVE LOGITS
    CHAT
    0.79
    à¼
    0.75
    ãĥĢ
    0.75
    ãĤĬ
    0.72
    ×Ļ
    0.69
    ª
    0.66
    isoft
    0.66
    tain
    0.64
    ËĪ
    0.63
    Slot
    0.63
    Activations Density 0.157%

    No Known Activations