© 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. 22889
    Prev
    Next
    INDEX
    Explanations

    mentions of foam-related items or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to foam in various contexts

    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
    HCR
    -0.80
     Restaur
    -0.65
    orate
    -0.63
    abet
    -0.63
    eering
    -0.62
    Interstitial
    -0.62
     Predict
    -0.61
    cript
    -0.61
     Relations
    -0.60
     Places
    -0.60
    POSITIVE LOGITS
     foam
    1.11
     latex
    0.98
     insulation
    0.92
    odox
    0.82
    avored
    0.79
    olicy
    0.79
     Fo
    0.75
    obar
    0.74
    thora
    0.74
    oline
    0.73
    Activations Density 0.008%

    No Known Activations