© 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. 7-RES-JB
    11. 23113
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing or seeking information about a topic

    oai_token-act-pair · gpt-3.5-turbo

    references to time and dates in the context of events or announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ondo
    -0.70
    /-
    -0.68
    merce
    -0.67
    oyal
    -0.65
    stall
    -0.64
    portation
    -0.63
    ploy
    -0.63
    oom
    -0.62
    estate
    -0.62
    oya
    -0.61
    POSITIVE LOGITS
     PBS
    0.65
     Rath
    0.65
     Pastebin
    0.64
     firsthand
    0.63
     Werner
    0.63
     Wik
    0.62
     pdf
    0.61
     wiki
    0.60
     Wired
    0.60
     Klaus
    0.60
    Activations Density 0.658%

    No Known Activations