© 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. 1-RES-JB
    11. 14984
    Prev
    Next
    INDEX
    Explanations

    references to the term "Legion", which could be related to a variety of contexts such as a disease, organization, or group of individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to "Legion" and its variations

    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
    ahn
    -0.71
     straw
    -0.65
    ramid
    -0.65
     CHO
    -0.65
     refere
    -0.64
    bid
    -0.62
    gered
    -0.62
     srf
    -0.62
    Bloomberg
    -0.59
     trending
    -0.58
    POSITIVE LOGITS
    naire
    1.93
    naires
    1.76
     Legion
    1.34
     legion
    1.16
    arium
    0.87
    esses
    0.86
    aries
    0.85
     Legions
    0.83
     legions
    0.83
    BuyableInstoreAndOnline
    0.82
    Activations Density 0.008%

    No Known Activations