© 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. 3-RES-JB
    11. 23214
    Prev
    Next
    INDEX
    Explanations

    words related to types of medical procedures or treatments

    oai_token-act-pair · gpt-3.5-turbo

    words related to specific types of structures or patterns, often within a technical or analytical context

    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
     Investors
    -0.85
     Sacrament
    -0.80
     Market
    -0.80
     Partners
    -0.78
     Dynamics
    -0.78
    HCR
    -0.78
    Ô
    -0.77
     Debt
    -0.77
     Retail
    -0.76
     Ducks
    -0.75
    POSITIVE LOGITS
    iably
    0.90
    uously
    0.89
    icy
    0.88
    ifiable
    0.86
    icol
    0.81
    ib
    0.80
     jour
    0.80
    osc
    0.80
    ented
    0.79
    iously
    0.79
    Activations Density 0.056%

    No Known Activations