© 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. 4-RES-JB
    11. 10318
    Prev
    Next
    INDEX
    Explanations

    technical terms related to data analysis and mathematical modeling, specifically focusing on the concept of "parameters."

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical parameters in a scientific or technical context

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

    No Comments

    Negative Logits
    luaj
    -0.75
    ILLE
    -0.74
    BY
    -0.72
    bery
    -0.70
    minster
    -0.69
     coli
    -0.68
    PO
    -0.67
    lez
    -0.66
    cler
    -0.66
    IDA
    -0.65
    POSITIVE LOGITS
     parameters
    1.07
    eters
    0.98
    eter
    0.88
    ilitary
    0.85
    izes
    0.84
    ities
    0.83
    izable
    0.80
    ised
    0.79
    ized
    0.79
    eers
    0.75
    Activations Density 0.011%

    No Known Activations