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

    Neuronpedia

    Jacobian LensNEW
    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. 21234
    Prev
    Next
    INDEX
    Explanations

    phrases indicating knowledge or expertise in various subjects

    oai_token-act-pair · gpt-3.5-turbo

    claims of knowledge or understanding about various subjects

    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
     Featured
    -0.72
    hement
    -0.70
    atform
    -0.70
    cation
    -0.68
    yrim
    -0.66
    erate
    -0.65
    ittal
    -0.65
    ission
    -0.64
    vertisement
    -0.63
    eworthy
    -0.63
    POSITIVE LOGITS
     intimately
    0.88
     whereabouts
    0.83
     firsthand
    0.81
    CHAT
    0.77
     beforehand
    0.70
    âĨij
    0.69
     drill
    0.68
     instinctively
    0.68
     secret
    0.67
    æĿ
    0.67
    Activations Density 0.214%

    No Known Activations