© 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. 10-RES-JB
    11. 3106
    Prev
    Next
    INDEX
    Explanations

    references to screen resolutions and technical specifications

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of names or initials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zx
    -0.60
    xual
    -0.59
    Ö¼
    -0.59
     Shogun
    -0.58
    asio
    -0.58
    =-=-=-=-=-=-=-=-
    -0.57
    restrial
    -0.55
    ospons
    -0.55
     Masquerade
    -0.55
    alion
    -0.55
    POSITIVE LOGITS
    rage
    0.64
    OLD
    0.64
    anchester
    0.60
     uncond
    0.59
    clinton
    0.58
    ited
    0.58
    arted
    0.58
    fm
    0.57
    uku
    0.54
    ãĥı
    0.54
    Activations Density 0.152%

    No Known Activations