© 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. 2778
    Prev
    Next
    INDEX
    Explanations

    phrases related to the term "BAT"

    oai_token-act-pair · gpt-3.5-turbo

    references to bats, particularly in contexts related to events or incidents

    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
     rall
    -0.71
    rete
    -0.68
     slopes
    -0.68
     Entry
    -0.66
     Swed
    -0.65
     veil
    -0.64
    ende
    -0.63
     Turk
    -0.63
     conc
    -0.63
    pair
    -0.62
    POSITIVE LOGITS
    BAT
    3.33
     BAT
    2.47
    ICAN
    2.05
     Recovery
    1.09
    dark
    0.98
    Spons
    0.95
    attery
    0.95
    asma
    0.94
    Developer
    0.94
    Community
    0.93
    Activations Density 0.064%

    No Known Activations