© 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. 1-RES-JB
    11. 22052
    Prev
    Next
    INDEX
    Explanations

    words related to violent or forceful actions

    oai_token-act-pair · gpt-3.5-turbo

    words related to various forms of "ashing" and "ashed" actions or states

    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
     cone
    -0.79
    communication
    -0.70
    thora
    -0.69
    brance
    -0.69
     govern
    -0.67
    cussion
    -0.67
     duct
    -0.67
    neapolis
    -0.67
    iversal
    -0.66
     neur
    -0.65
    POSITIVE LOGITS
    ashing
    1.12
    ashed
    1.08
    ashes
    1.00
    ASH
    0.94
    Sab
    0.86
    ãĥĺ
    0.85
    Hur
    0.84
     Rebell
    0.80
    ash
    0.77
    ELF
    0.76
    Activations Density 0.009%

    No Known Activations