© 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. 4034
    Prev
    Next
    INDEX
    Explanations

    chemical substances and related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to consumable and functional items or substances

    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
     Refuge
    -0.72
    fuck
    -0.71
     Weinstein
    -0.69
     Fired
    -0.68
    beard
    -0.67
    boro
    -0.67
     Hath
    -0.67
    frog
    -0.67
    leigh
    -0.66
     Daddy
    -0.65
    POSITIVE LOGITS
    ants
    1.20
    ators
    1.12
    ables
    1.08
    ational
    1.06
    ant
    1.06
    iencies
    1.01
    ations
    0.98
    ricular
    0.98
    estate
    0.97
    ancies
    0.96
    Activations Density 0.020%

    No Known Activations