© 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. 24026
    Prev
    Next
    INDEX
    Explanations

    strong opinions or beliefs stated as facts

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to beliefs, assumptions, and perceptions

    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
    aband
    -0.76
    quer
    -0.70
    yna
    -0.68
    xtap
    -0.64
    iffe
    -0.63
    miah
    -0.62
    mes
    -0.61
    ortunately
    -0.61
    artney
    -0.59
    umbn
    -0.59
    POSITIVE LOGITS
     that
    0.79
    ariat
    0.77
    lessness
    0.75
    worthiness
    0.71
    hood
    0.69
    uality
    0.69
    tale
    0.69
     about
    0.68
    IONS
    0.67
    that
    0.66
    Activations Density 0.296%

    No Known Activations