© 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. 7-RES-JB
    11. 1655
    Prev
    Next
    INDEX
    Explanations

    phrases indicating positive or negative impact

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating causal relationships or significant impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Memor
    -0.72
     sale
    -0.70
     dies
    -0.65
     Sale
    -0.64
     nig
    -0.63
     likes
    -0.63
     Anniversary
    -0.62
     tables
    -0.62
     Writ
    -0.61
     socket
    -0.61
    POSITIVE LOGITS
    FML
    1.13
     overshadow
    0.96
     outweigh
    0.93
     attest
    0.88
     complicate
    0.88
     suffice
    0.85
    quickShipAvailable
    0.85
     outwe
    0.83
     warranted
    0.82
     preclude
    0.81
    Activations Density 0.348%

    No Known Activations