© 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. 4-RES-JB
    11. 624
    Prev
    Next
    INDEX
    Explanations

    specific words related to academic research, such as "thesis" and "dissertation."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the words "thesis" and "dissertation."

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

    No Comments

    Negative Logits
    icz
    -0.74
    obby
    -0.72
    nels
    -0.72
    gm
    -0.71
    theless
    -0.71
    atility
    -0.69
    tering
    -0.66
    bies
    -0.65
    tn
    -0.65
    outube
    -0.63
    POSITIVE LOGITS
    ertation
    1.28
     thesis
    1.16
    uates
    0.98
     dissertation
    0.90
    ually
    0.87
    pai
    0.83
    iary
    0.79
    doc
    0.76
    endish
    0.73
     doctoral
    0.70
    Activations Density 0.010%

    No Known Activations