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

    Neuronpedia

    APICircuit 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. 585
    Prev
    Next
    INDEX
    Explanations

    URLs related to GitHub profiles

    oai_token-act-pair · gpt-3.5-turbo

    web addresses and URL patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    URLs, numerical values, and structured data elements.

    oai_token-act-pair · gpt-4oTriggered by @tatsatx
    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
    è»
    -0.50
    aterasu
    -0.46
     âĵĺ
    -0.43
    PLA
    -0.43
    terness
    -0.43
    FORE
    -0.42
    é£
    -0.42
    éĸ
    -0.41
     Airbus
    -0.40
    oola
    -0.39
    POSITIVE LOGITS
    sheet
    0.48
    sic
    0.46
     sans
    0.44
     minus
    0.43
    sheets
    0.40
     gimmick
    0.40
     Powered
    0.39
    wcs
    0.39
     dunno
    0.39
     unison
    0.39
    Activations Density 3.236%

    No Known Activations