© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 10006
    Prev
    Next
    INDEX
    Explanations

    terms related to nitrogen compounds or chemical elements containing the word "nit"

    oai_token-act-pair · gpt-3.5-turbo

    mentions and variations of the word "nitrogen."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Alz
    -0.75
    ILY
    -0.72
    REDACTED
    -0.66
     McDonnell
    -0.65
    ITED
    -0.63
     Presidency
    -0.61
     Butterfly
    -0.60
     Gle
    -0.60
    ITNESS
    -0.59
    tips
    -0.59
    POSITIVE LOGITS
    rous
    1.41
    rogen
    1.33
    picking
    1.26
    ropolis
    1.10
    rates
    1.09
    rification
    1.08
    rite
    1.06
    pick
    1.06
    ric
    1.04
    rate
    1.04
    Activations Density 0.027%

    No Known Activations