© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2487
    Prev
    Next
    INDEX
    Explanations

    the word "word" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to specific words and terms

    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
    jri
    -0.86
     millenn
    -0.69
    ockets
    -0.69
    âĹ¼
    -0.67
    aukee
    -0.66
    oÄŁ
    -0.65
     throats
    -0.63
    DERR
    -0.63
    ierrez
    -0.61
    aples
    -0.61
    POSITIVE LOGITS
     itself
    0.93
    ultimate
    0.89
     '
    0.83
     "
    0.78
    icide
    0.76
     \"
    0.70
    00000000
    0.70
     synonymous
    0.70
     "-
    0.68
    plate
    0.67
    Activations Density 0.089%

    No Known Activations