© 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. 2-RES-JB
    11. 1725
    Prev
    Next
    INDEX
    Explanations

    specific abbreviations or codes with the pattern "PF" followed by a number, particularly "PF9" and "PF10."

    oai_token-act-pair · gpt-3.5-turbo

    references to player statistics or performance metrics in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ£
    -0.74
     cort
    -0.72
    rawdownloadcloneembedreportprint
    -0.71
    è¦ļéĨĴ
    -0.70
    aneously
    -0.69
     winner
    -0.68
    âĸ¬
    -0.68
    ctors
    -0.66
    score
    -0.66
    link
    -0.62
    POSITIVE LOGITS
    olicy
    1.05
     PF
    1.02
    umes
    1.01
    ratulations
    0.86
    acebook
    0.82
    OTUS
    0.79
    ols
    0.79
    ornia
    0.77
    ridges
    0.77
    omez
    0.76
    Activations Density 0.023%

    No Known Activations