© 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. 12514
    Prev
    Next
    INDEX
    Explanations

    references to various forms of communication or expression, such as speeches, confessions, and testimonies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to personal narratives and significant actions or events

    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
    iland
    -0.76
    psc
    -0.72
    enegger
    -0.72
    ERO
    -0.67
    stad
    -0.65
    £ı
    -0.65
    mobi
    -0.65
    react
    -0.64
    effect
    -0.64
    Ĭ±
    -0.63
    POSITIVE LOGITS
     worn
    0.77
     holder
    0.69
     belonging
    0.69
     bestowed
    0.68
     among
    0.67
     Coil
    0.64
    lessness
    0.64
     exercised
    0.64
     uttered
    0.63
     whistleblowers
    0.60
    Activations Density 0.563%

    No Known Activations