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. 2-RES-JB
    6. 13086
    Prev
    Next
    INDEX
    Explanations

    words related to conducting searches or investigations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the words "search" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    noxious
    -0.77
    minecraft
    -0.76
    death
    -0.74
    ivari
    -0.71
    cil
    -0.70
    Downloadha
    -0.70
    iHUD
    -0.69
    Production
    -0.68
    interstitial
    -0.68
    cigarette
    -0.67
    POSITIVE LOGITS
     searches
    1.00
     searching
    0.90
     searched
    0.87
     search
    0.85
     queries
    0.83
     warrant
    0.81
     sear
    0.79
     frantically
    0.78
     warrants
    0.75
    emouth
    0.75
    Activations Density 0.022%

    No Known Activations