© 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. 16448
    Prev
    Next
    INDEX
    Explanations

    economic and financial terms or concepts

    oai_token-act-pair · gpt-3.5-turbo

    quantitative data and measurements related to income, probability, mass, and efficiency

    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
    nos
    -0.66
    spection
    -0.64
    emon
    -0.61
    assion
    -0.60
     womb
    -0.60
    bsp
    -0.59
     Plenty
    -0.59
    zan
    -0.58
    tics
    -0.58
    gery
    -0.57
    POSITIVE LOGITS
     ratios
    1.17
     ratio
    1.14
     difference
    1.10
     distributions
    1.01
     differential
    1.01
     coefficients
    1.00
     disparity
    0.99
     gradient
    0.98
     characteristics
    0.98
     coefficient
    0.97
    Activations Density 0.275%

    No Known Activations