© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 21439
    Prev
    Next
    INDEX
    Explanations

    numbers with measurement units

    oai_token-act-pair · gpt-3.5-turbo

    numerical values, particularly related to measurements or quantities

    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
    arial
    -0.72
    antically
    -0.71
    istry
    -0.67
    establishment
    -0.62
    awaru
    -0.62
     fencing
    -0.59
     agre
    -0.59
     destro
    -0.59
     Jagu
    -0.58
     concess
    -0.58
    POSITIVE LOGITS
     tablespoons
    0.93
     SHARES
    0.91
     Corinthians
    0.86
     Months
    0.85
     hrs
    0.84
    nd
    0.83
    âĺħ
    0.79
    Reviewed
    0.79
     hr
    0.79
    0000000
    0.79
    Activations Density 0.095%

    No Known Activations