© 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. 1-RES-JB
    11. 10309
    Prev
    Next
    INDEX
    Explanations

    names or words containing the sequence "hn" in them

    oai_token-act-pair · gpt-3.5-turbo

    names of people or characters, particularly surnames

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĹ¼
    -0.82
    accompan
    -0.73
     Yemeni
    -0.66
    Premium
    -0.65
     bearer
    -0.65
    Pokemon
    -0.65
     Avalanche
    -0.65
     Primal
    -0.64
    Maximum
    -0.64
    drawn
    -0.63
    POSITIVE LOGITS
    hn
    1.43
    agar
    1.10
    eman
    1.05
    swer
    0.92
    hm
    0.90
    quist
    0.90
    avy
    0.88
    asy
    0.88
    hak
    0.88
    hr
    0.87
    Activations Density 0.004%

    No Known Activations