© 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. 4-RES-JB
    11. 2292
    Prev
    Next
    INDEX
    Explanations

    mentions of foam products

    oai_token-act-pair · gpt-3.5-turbo

    references to foam and its various uses or applications

    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
    HCR
    -0.79
     Restaur
    -0.70
    cript
    -0.66
    sen
    -0.66
    OTO
    -0.66
    hip
    -0.64
    Topic
    -0.64
    Interstitial
    -0.63
    pid
    -0.62
    hips
    -0.62
    POSITIVE LOGITS
     foam
    1.03
     latex
    0.96
    avored
    0.89
     insulation
    0.85
     Fo
    0.81
    obar
    0.80
    zz
    0.75
    ogle
    0.74
    udge
    0.74
    olicy
    0.74
    Activations Density 0.009%

    No Known Activations