© 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. 10235
    Prev
    Next
    INDEX
    Explanations

    numerical measurements and statistical information

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistical analysis in research contexts

    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
    pmwiki
    -0.75
    ulkan
    -0.74
    stories
    -0.68
     leasing
    -0.66
    glers
    -0.64
    xit
    -0.64
    angible
    -0.64
    phies
    -0.64
    prus
    -0.63
    Kick
    -0.62
    POSITIVE LOGITS
     coefficient
    1.07
    mean
    1.03
     df
    1.02
     odds
    0.99
     âĪĴ
    0.99
     ±
    0.97
     CI
    0.92
     +/-
    0.91
     RR
    0.89
     rs
    0.89
    Activations Density 0.122%

    No Known Activations