© 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 EvalsExportsinterp-engineNEWAPI 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. 4-RES-JB
    11. 1530
    Prev
    Next
    INDEX
    Explanations

    numbers or quantities mentioned in relation to something else

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "or" used in various contexts or quantifications

    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
     Reporter
    -0.73
    ECH
    -0.70
    ires
    -0.69
    OTOS
    -0.67
    VERTISEMENT
    -0.67
    ADVERTISEMENT
    -0.67
    Monitor
    -0.67
     VIDEOS
    -0.65
     Pony
    -0.63
    Mech
    -0.63
    POSITIVE LOGITS
    chard
    1.20
    ifice
    1.20
    acle
    1.14
    ific
    1.11
    nam
    1.07
    chid
    1.05
    lando
    1.01
    acular
    0.99
    thodox
    0.98
    acles
    0.97
    Activations Density 0.109%

    No Known Activations