© 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. 0-RES-JB
    11. 8366
    Prev
    Next
    INDEX
    Explanations

    words related to recognition and cognition

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cognitive recognition or awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     drip
    -0.69
     sewing
    -0.67
     heating
    -0.65
     drought
    -0.64
     basement
    -0.64
     pumps
    -0.64
     ERA
    -0.63
     nights
    -0.63
     pump
    -0.62
     desks
    -0.62
    POSITIVE LOGITS
    ogn
    4.62
    ognitive
    1.48
     Cogn
    1.34
    agn
    1.32
     cogn
    1.31
    recogn
    1.30
     Recogn
    1.26
    ompl
    1.19
    ocent
    1.15
    og
    1.06
    Activations Density 0.017%

    No Known Activations