© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 22370
    Prev
    Next
    INDEX
    Explanations

    words related to dental care

    oai_token-act-pair · gpt-3.5-turbo

    terms related to dental health or dentistry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Row
    -0.76
     congratulations
    -0.68
     wit
    -0.65
     Bom
    -0.63
     silhou
    -0.63
     Lion
    -0.62
     Romeo
    -0.62
     bund
    -0.61
     storm
    -0.60
     Spike
    -0.60
    POSITIVE LOGITS
    ental
    4.61
    ents
    1.71
    mental
    1.66
    ent
    1.60
    ented
    1.51
    ENT
    1.48
    enting
    1.46
    enth
    1.31
    enza
    1.30
    ential
    1.29
    Activations Density 0.011%

    No Known Activations