© 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. 7-RES-JB
    11. 2160
    Prev
    Next
    INDEX
    Explanations

    Spanish words related to various topics or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names or terms related to individuals or brands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chell
    -0.88
    lain
    -0.88
    rar
    -0.86
    rage
    -0.83
    loss
    -0.82
    rim
    -0.80
    rat
    -0.77
    mire
    -0.76
    inness
    -0.75
    ealing
    -0.74
    POSITIVE LOGITS
    aceae
    0.77
     Beans
    0.72
    ocamp
    0.71
    stal
    0.66
    omon
    0.65
    OUP
    0.64
    ppo
    0.64
    uble
    0.63
     mold
    0.63
     Strauss
    0.63
    Activations Density 0.106%

    No Known Activations