© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 6303
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or announcements, particularly those related to specific dates or venues

    oai_token-act-pair · gpt-3.5-turbo

    references to events, tournaments, and sites within a competitive or gaming context

    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
    uster
    -0.68
     antip
    -0.66
     apes
    -0.65
     trave
    -0.64
     consulate
    -0.63
     traffic
    -0.63
     eyeb
    -0.62
     passions
    -0.62
    ĪĴ
    -0.61
     crates
    -0.61
    POSITIVE LOGITS
     TBA
    0.72
     Begins
    0.66
     Provider
    0.66
     Goes
    0.65
     âĪ
    0.65
     Pt
    0.64
    eer
    0.64
    onica
    0.64
    :
    0.64
     guiName
    0.63
    Activations Density 0.180%

    No Known Activations