© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 15003
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names of specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and their actions or statuses

    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
    ierrez
    -0.70
    rontal
    -0.65
    geoning
    -0.61
    noon
    -0.61
    artisan
    -0.61
    =-=-
    -0.59
     Alive
    -0.58
     MFT
    -0.56
    mony
    -0.56
    Chair
    -0.54
    POSITIVE LOGITS
     fuss
    0.95
    ãĤ´
    0.84
     doing
    0.83
     accomplished
    0.81
     Doing
    0.81
     entail
    0.79
     entails
    0.78
     wrought
    0.77
     meant
    0.76
     Learned
    0.74
    Activations Density 0.309%

    No Known Activations