© 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. 7-RES-JB
    11. 12598
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to battles

    oai_token-act-pair · gpt-3.5-turbo

    references to battles or competitive confrontations in titles and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ascript
    -0.82
    ols
    -0.75
    entric
    -0.69
    ophone
    -0.68
    Property
    -0.67
    essage
    -0.67
    atever
    -0.67
    ensibly
    -0.66
    oba
    -0.65
    egu
    -0.65
    POSITIVE LOGITS
     roy
    1.09
    front
    1.06
    cru
    0.97
     Royale
    0.94
    axe
    0.91
    mage
    0.85
    cry
    0.84
     fought
    0.83
    force
    0.82
     battles
    0.79
    Activations Density 0.028%

    No Known Activations