© 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. 18645
    Prev
    Next
    INDEX
    Explanations

    information and details related to investigations or queries

    oai_token-act-pair · gpt-3.5-turbo

    references to information, particularly in the context of investigations or inquiries

    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
    emale
    -0.70
     Carbuncle
    -0.64
     lifetime
    -0.61
    ortunately
    -0.61
    ovie
    -0.60
     Vengeance
    -0.59
    ategory
    -0.59
     Balanced
    -0.58
    xtap
    -0.58
    Zone
    -0.58
    POSITIVE LOGITS
     regarding
    1.25
     concerning
    1.09
     about
    1.08
     glean
    1.02
     relating
    0.98
     pertaining
    0.97
     detailing
    0.96
     ABOUT
    0.93
     clues
    0.85
     confirming
    0.84
    Activations Density 0.200%

    No Known Activations