© 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. 3-RES-JB
    11. 2966
    Prev
    Next
    INDEX
    Explanations

    references to searches or searching activities

    oai_token-act-pair · gpt-3.5-turbo

    references to search activities or warrants

    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
    noxious
    -0.78
    ivari
    -0.73
    minecraft
    -0.73
    fortune
    -0.70
    Downloadha
    -0.70
    earned
    -0.68
    Production
    -0.68
    absolute
    -0.67
    published
    -0.66
     Sandwich
    -0.66
    POSITIVE LOGITS
     warrant
    0.88
     warrants
    0.80
    alysed
    0.77
     Warrant
    0.76
     searches
    0.75
     engines
    0.74
    emouth
    0.70
    alogy
    0.69
     microsc
    0.69
     search
    0.68
    Activations Density 0.016%

    No Known Activations