© 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. 4-RES-JB
    11. 17026
    Prev
    Next
    INDEX
    Explanations

    materials related to technology and engineering, specifically carbon fiber and metals like stainless steel

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to materials and construction

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

    No Comments

    Negative Logits
    cffffcc
    -0.99
    SPONSORED
    -0.87
    arios
    -0.84
    zee
    -0.83
    reon
    -0.71
    Leary
    -0.71
    Fla
    -0.70
    Dispatch
    -0.69
    iddles
    -0.68
     Hungry
    -0.68
    POSITIVE LOGITS
     oxide
    1.15
     alloy
    1.15
     coated
    1.11
     coating
    1.08
     ceramic
    1.08
     silicone
    1.05
     molded
    1.04
     rubber
    1.04
     resin
    1.03
     mesh
    1.03
    Activations Density 0.143%

    No Known Activations