© 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. 3-RES-JB
    11. 9522
    Prev
    Next
    INDEX
    Explanations

    references to the Rosetta mission

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Rosetta"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.81
    ulhu
    -0.77
     Countdown
    -0.69
     à¨
    -0.67
     Rasmussen
    -0.66
     warrants
    -0.65
    endants
    -0.65
     magnitude
    -0.63
     Judicial
    -0.62
    ³³³
    -0.62
    POSITIVE LOGITS
    etta
    1.05
    lyn
    1.05
    enth
    0.99
    alez
    0.96
    enthal
    0.95
    burn
    0.93
    acea
    0.90
    coe
    0.90
    yth
    0.88
    issance
    0.88
    Activations Density 0.008%

    No Known Activations