© 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. 0-RES-JB
    11. 9392
    Prev
    Next
    INDEX
    Explanations

    text related to the concept of importance or significance

    oai_token-act-pair · gpt-3.5-turbo

    references to significant or crucial topics, especially in a context suggesting improvement or necessity

    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
     betray
    -0.77
     slaves
    -0.74
     betrayed
    -0.69
     slut
    -0.67
     Divide
    -0.64
     swe
    -0.62
     captured
    -0.62
     coll
    -0.62
     Slate
    -0.62
     Jail
    -0.61
    POSITIVE LOGITS
    ential
    4.64
    entials
    2.63
    entially
    2.34
    ences
    1.70
    ence
    1.50
    enza
    1.48
    encing
    1.35
    encies
    1.33
    ents
    1.30
    ental
    1.27
    Activations Density 0.012%

    No Known Activations