© 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. 1-RES-JB
    11. 3946
    Prev
    Next
    INDEX
    Explanations

    terms related to over-dosage or over-use; includes terms like "overdosing," "overdone," and "overwriting."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "overd" related to overdoses and dependency issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.74
    auga
    -0.66
    dar
    -0.64
    Assembly
    -0.63
    =-=-=-=-
    -0.63
    STEM
    -0.62
    andum
    -0.61
    kie
    -0.61
     Pug
    -0.60
     Pathfinder
    -0.60
    POSITIVE LOGITS
     overd
    1.45
    raft
    0.91
    rawn
    0.90
    icter
    0.90
    ivery
    0.88
    rown
    0.82
    uates
    0.80
    irty
    0.80
    icates
    0.79
    owler
    0.79
    Activations Density 0.011%

    No Known Activations