© 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. 17556
    Prev
    Next
    INDEX
    Explanations

    numerical values tagged with a specific unit symbol

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical values, particularly those related to monetary amounts

    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
     GOODMAN
    -0.84
    yang
    -0.80
    eering
    -0.76
    ezvous
    -0.75
    endum
    -0.71
    gments
    -0.71
    hran
    -0.70
    orate
    -0.69
    ongyang
    -0.69
    chard
    -0.68
    POSITIVE LOGITS
     ILCS
    1.35
    75
    0.99
    475
    0.89
    80
    0.87
    655
    0.86
    8000
    0.85
    875
    0.85
    680
    0.85
    ength
    0.84
    00000
    0.84
    Activations Density 0.025%

    No Known Activations