© 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. 3785
    Prev
    Next
    INDEX
    Explanations

    words related to confrontation or conflict

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to confrontation and family relationships

    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
     Ans
    -0.74
    glers
    -0.70
    lar
    -0.68
     boxes
    -0.65
     Peb
    -0.64
     Oro
    -0.63
     Henderson
    -0.63
     Whe
    -0.63
     Box
    -0.62
     Pengu
    -0.62
    POSITIVE LOGITS
    rait
    0.88
    ipeg
    0.83
    minded
    0.82
    working
    0.80
    itudes
    0.79
    sburg
    0.79
    imer
    0.79
    ranged
    0.79
    ravel
    0.79
    son
    0.78
    Activations Density 0.033%

    No Known Activations