Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 6870
    Prev
    Next
    INDEX
    Explanations

    phrases related to nitric compounds

    oai_token-act-pair · gpt-3.5-turbo

    references to nitrogen compounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngth
    -0.90
    xual
    -0.89
    OHN
    -0.75
    DragonMagazine
    -0.75
    hip
    -0.74
    NetMessage
    -0.72
     [|
    -0.71
    ILY
    -0.70
     Alz
    -0.69
    adena
    -0.69
    POSITIVE LOGITS
    rous
    1.10
    picking
    1.10
    rates
    1.02
     nit
    1.00
    nit
    0.94
    rogen
    0.93
    pick
    0.85
    rate
    0.84
    rification
    0.84
     Nit
    0.84
    Activations Density 0.010%

    No Known Activations