© 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. 11-RES-JB
    11. 22530
    Prev
    Next
    INDEX
    Explanations

    content encoding special characters in a document

    oai_token-act-pair · gpt-3.5-turbo

    numbers and numerical values within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Everett
    -0.83
     butterflies
    -0.83
     Orlando
    -0.83
     continental
    -0.82
    ortunately
    -0.82
     Comet
    -0.82
     butterfly
    -0.81
     Dawkins
    -0.81
     tornado
    -0.80
     temptation
    -0.80
    POSITIVE LOGITS
    Published
    1.61
    Refer
    1.61
    Meanwhile
    1.60
    According
    1.60
    Moreover
    1.60
    Earlier
    1.59
    Sources
    1.58
    Besides
    1.57
    Regarding
    1.57
    Talking
    1.56
    Activations Density 0.238%

    No Known Activations