© 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. 10503
    Prev
    Next
    INDEX
    Explanations

    names of locations and people

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and terms related to specific people and places

    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
     rooting
    -0.76
     metic
    -0.75
     stump
    -0.69
     craving
    -0.64
     unsett
    -0.63
     departing
    -0.63
     roundup
    -0.63
     heav
    -0.62
     mildly
    -0.62
    ermott
    -0.62
    POSITIVE LOGITS
    gard
    1.22
    ner
    1.03
    gart
    0.97
    ners
    0.92
    alist
    0.91
    ente
    0.89
    ility
    0.88
    lasses
    0.88
    pipe
    0.88
    ens
    0.87
    Activations Density 0.025%

    No Known Activations