© 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. 8-RES-JB
    11. 6812
    Prev
    Next
    INDEX
    Explanations

    numerical values and technical jargon

    oai_token-act-pair · gpt-3.5-turbo

    elements related to technical specifications and numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gow
    -0.66
     Toledo
    -0.65
    wer
    -0.64
     Kad
    -0.63
     Elk
    -0.63
     Tant
    -0.63
    loo
    -0.62
    eer
    -0.61
     haw
    -0.60
     Haku
    -0.59
    POSITIVE LOGITS
    1
    1.38
     1
    1.11
    ãĥĺãĥ©
    1.05
    2
    0.94
    ĥ
    0.83
    1001
    0.76
    ãĤ¹
    0.76
    ania
    0.76
    ½
    0.76
     ½
    0.75
    Activations Density 0.221%

    No Known Activations