© 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. 10206
    Prev
    Next
    INDEX
    Explanations

    versions or editions of something

    oai_token-act-pair · gpt-3.5-turbo

    references to different adaptations or variations of something

    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
    redo
    -0.68
    ãĤī
    -0.67
    APTER
    -0.67
    usters
    -0.65
     prod
    -0.63
    eneg
    -0.59
    rones
    -0.59
    oros
    -0.59
    row
    -0.58
    mong
    -0.58
    POSITIVE LOGITS
     thereof
    1.30
     of
    1.05
     version
    0.72
    etting
    0.71
    etter
    0.69
    esan
    0.68
     Of
    0.68
    cens
    0.67
     versions
    0.67
    Versions
    0.66
    Activations Density 0.050%

    No Known Activations