Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 5716
    Prev
    Next
    INDEX
    Explanations

    phrases related to searching or going through items or information

    oai_token-act-pair · gpt-3.5-turbo

    instances of searching or navigating through various types of content or information

    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
    none
    -0.67
    kiss
    -0.66
    FLAG
    -0.64
    ajor
    -0.64
    roit
    -0.63
    CVE
    -0.63
    FE
    -0.62
    vant
    -0.61
    touch
    -0.61
    isin
    -0.61
    POSITIVE LOGITS
     menus
    1.07
     archives
    1.03
     databases
    1.03
     folders
    0.87
     bins
    0.87
     QR
    0.85
     shelves
    0.85
     wreckage
    0.84
     histories
    0.82
     database
    0.81
    Activations Density 0.208%

    No Known Activations