© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 19612
    Prev
    Next
    INDEX
    Explanations

    references to physical entrances or exits

    oai_token-act-pair · gpt-3.5-turbo

    references to entrances in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    netflix
    -0.66
    grave
    -0.64
    abi
    -0.64
    enegger
    -0.63
    yan
    -0.62
    uku
    -0.62
    ilot
    -0.62
    ondo
    -0.62
    unker
    -0.61
    verbs
    -0.61
    POSITIVE LOGITS
     entrance
    1.13
     entrances
    1.02
     gates
    0.89
     thereto
    0.87
     doors
    0.84
    prise
    0.83
    stones
    0.82
    pole
    0.82
    keeper
    0.81
    tainment
    0.81
    Activations Density 0.011%

    No Known Activations