© 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. 15699
    Prev
    Next
    INDEX
    Explanations

    words related to data processing and information transmission

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to data collection and processing

    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
    luaj
    -0.70
    haw
    -0.65
    ahu
    -0.65
     Pratt
    -0.64
     è£ıç
    -0.63
     Slaughter
    -0.63
    STER
    -0.63
    KK
    -0.62
     Payne
    -0.62
    hoe
    -0.61
    POSITIVE LOGITS
     predetermined
    1.23
     disparate
    1.16
     different
    1.15
     specific
    1.14
     discrete
    1.14
     fewer
    1.10
     unrelated
    1.10
     arbitrary
    1.09
     successive
    1.08
     oneself
    1.07
    Activations Density 0.411%

    No Known Activations