© 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. 3064
    Prev
    Next
    INDEX
    Explanations

    QR codes

    oai_token-act-pair · gpt-3.5-turbo

    references to QR codes and the Quran

    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
     DRAG
    -0.75
    éĹĺ
    -0.74
    rawdownloadcloneembedreportprint
    -0.67
    ersen
    -0.65
    holm
    -0.65
     PLUS
    -0.65
    å°Ĩ
    -0.64
    STE
    -0.64
    orp
    -0.64
     Pioneer
    -0.63
    POSITIVE LOGITS
    atar
    1.03
    ane
    0.81
    ĵĺ
    0.80
    Scroll
    0.79
    agan
    0.75
    ays
    0.75
    ĥ
    0.75
    geries
    0.74
    agonal
    0.74
    ĸļ
    0.74
    Activations Density 0.011%

    No Known Activations