© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 2517
    Prev
    Next
    INDEX
    Explanations

    mentions of capsules or similar containers

    oai_token-act-pair · gpt-3.5-turbo

    terms related to capsules and their various contexts

    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
    PUT
    -0.72
    went
    -0.67
    nee
    -0.67
    cipl
    -0.67
     Episcopal
    -0.66
    ances
    -0.63
    stood
    -0.63
    à¨
    -0.62
    armed
    -0.62
    Beg
    -0.61
    POSITIVE LOGITS
     capsule
    1.14
     capsules
    0.96
    ules
    0.86
     liner
    0.78
    anut
    0.77
    atel
    0.73
     pod
    0.73
    ule
    0.73
    etry
    0.73
    achev
    0.72
    Activations Density 0.006%

    No Known Activations