© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 3820
    Prev
    Next
    INDEX
    Explanations

    phrases related to intense conflict or struggle

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of battle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atever
    -0.73
    ols
    -0.72
    ħĭ
    -0.71
    Ħ¢
    -0.70
    missible
    -0.66
    perm
    -0.66
    ascript
    -0.66
    redit
    -0.65
    olls
    -0.65
    Property
    -0.64
    POSITIVE LOGITS
     battles
    0.97
     roy
    0.94
    front
    0.92
    axe
    0.91
    naire
    0.87
    wagon
    0.87
    cru
    0.85
     Royale
    0.84
     battle
    0.83
    riors
    0.82
    Activations Density 0.022%

    No Known Activations