© 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. 4-RES-JB
    11. 2085
    Prev
    Next
    INDEX
    Explanations

    names or terms ending with 'hn', 'hl', or 'hm'

    oai_token-act-pair · gpt-3.5-turbo

    sequences of characters that represent names or identifiers

    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
    âĹ¼
    -0.97
    BuyableInstoreAndOnline
    -0.87
    DragonMagazine
    -0.83
    accompan
    -0.78
    multipl
    -0.78
    Premium
    -0.72
    cens
    -0.72
     indo
    -0.71
     Kurd
    -0.71
    staking
    -0.69
    POSITIVE LOGITS
    agar
    1.17
    eman
    1.02
    hn
    1.02
    igger
    0.92
    hak
    0.91
    avy
    0.89
    quist
    0.89
    hardt
    0.85
    othal
    0.83
    ihil
    0.82
    Activations Density 0.009%

    No Known Activations