© 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. 7690
    Prev
    Next
    INDEX
    Explanations

    keywords related to the term "Defenders" used in various contexts, potentially including a TV series, sports teams, organizations, and laws

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Defenders" in various contexts

    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
    pool
    -0.72
     Motorsport
    -0.66
     centrif
    -0.64
    onson
    -0.63
     driveway
    -0.63
     ignition
    -0.62
    Leary
    -0.62
     escal
    -0.62
     aggregate
    -0.62
     pools
    -0.61
    POSITIVE LOGITS
     Defenders
    2.52
     Defender
    2.00
    angered
    1.68
    idered
    1.59
    ruct
    1.12
     Crisis
    1.08
    counter
    1.05
     plight
    0.96
    ËĪ
    0.93
    agascar
    0.91
    Activations Density 0.060%

    No Known Activations