© 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. 9-RES-JB
    11. 13810
    Prev
    Next
    INDEX
    Explanations

    phrases related to biological mechanisms and medical processes

    oai_token-act-pair · gpt-3.5-turbo

    scientific terminology related to biological mechanisms and neural processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Kids
    -0.87
    Money
    -0.80
    wered
    -0.80
    Britain
    -0.75
    Advertisement
    -0.75
    Numbers
    -0.75
    today
    -0.74
     Journalism
    -0.74
     Mist
    -0.73
     Parkway
    -0.73
    POSITIVE LOGITS
     endogenous
    1.45
     phenotype
    1.37
     âĪ¼
    1.35
     inhibition
    1.31
     inhibit
    1.27
     phen
    1.27
     enz
    1.27
     metabolic
    1.21
     facult
    1.21
     β
    1.21
    Activations Density 0.816%

    No Known Activations