© 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. 1-RES-JB
    11. 21985
    Prev
    Next
    INDEX
    Explanations

    terms related to research activities or institutes

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the word "Research" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĶĢâĶĢ
    -0.64
    same
    -0.64
     Garfield
    -0.64
    vous
    -0.64
    mpeg
    -0.64
     femin
    -0.63
    zzi
    -0.63
    asar
    -0.62
    FAULT
    -0.61
    EMA
    -0.60
    POSITIVE LOGITS
    research
    0.97
     Research
    0.97
     Laboratory
    0.92
    Research
    0.92
     Advis
    0.86
     Associates
    0.84
     research
    0.83
     Advisor
    0.83
     Laboratories
    0.83
     Institute
    0.81
    Activations Density 0.012%

    No Known Activations