© 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. 11304
    Prev
    Next
    INDEX
    Explanations

    references to icons or iconic figures

    oai_token-act-pair · gpt-3.5-turbo

    references to icons and iconography

    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
    erer
    -0.65
     reliance
    -0.63
     fundament
    -0.62
    EE
    -0.60
    %%%%
    -0.60
    orney
    -0.59
     unborn
    -0.59
    ecause
    -0.58
     dup
    -0.57
    ying
    -0.57
    POSITIVE LOGITS
    icon
    1.19
    nect
    1.13
    itus
    1.02
    fig
    0.91
    ico
    0.90
    ically
    0.89
    icons
    0.87
    xon
    0.85
    æ©
    0.85
    ophon
    0.84
    Activations Density 0.017%

    No Known Activations