© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 5236
    Prev
    Next
    INDEX
    Explanations

    words related to academia and industry collaboration

    oai_token-act-pair · gpt-3.5-turbo

    terms related to academia and interdisciplinary studies

    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
     stride
    -0.62
     retaliate
    -0.61
     destro
    -0.57
    ardless
    -0.57
     thrott
    -0.57
    pload
    -0.57
     blockers
    -0.56
     flakes
    -0.56
     runoff
    -0.54
     unpredict
    -0.54
    POSITIVE LOGITS
     Scholars
    0.73
     Examination
    0.66
     scholars
    0.65
     scholar
    0.65
     Colleges
    0.64
     Degree
    0.64
     scholarly
    0.64
     pse
    0.63
     lecturer
    0.63
     professors
    0.63
    Activations Density 1.276%

    No Known Activations