© 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. 4-RES-JB
    11. 16153
    Prev
    Next
    INDEX
    Explanations

    rank and military titles

    oai_token-act-pair · gpt-3.5-turbo

    the presence of notable figures or authorities in a context

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

    No Comments

    Negative Logits
    uner
    -0.76
    andra
    -0.74
     challeng
    -0.74
    izu
    -0.72
    inki
    -0.71
    itia
    -0.70
    ahime
    -0.70
     fermented
    -0.68
    bley
    -0.67
    oked
    -0.66
    POSITIVE LOGITS
    ItemTracker
    0.83
     Afterwards
    0.78
     Paste
    0.77
     Surge
    0.74
     Huss
    0.73
     Equip
    0.72
    Org
    0.72
    Lt
    0.71
     Everywhere
    0.69
     Og
    0.68
    Activations Density 0.119%

    No Known Activations