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. 4-RES-JB
    6. 5300
    Prev
    Next
    INDEX
    Explanations

    URLs

    oai_token-act-pair · gpt-3.5-turbo

    URLs or web links

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

    No Comments

    Negative Logits
     leaflets
    -0.79
     Shade
    -0.71
     bark
    -0.70
     clin
    -0.68
     Lans
    -0.67
     Awakens
    -0.66
     infiltr
    -0.66
     proced
    -0.65
     Obi
    -0.64
     Vale
    -0.64
    POSITIVE LOGITS
    pmwiki
    1.21
    sites
    1.08
    wp
    1.07
    archives
    1.04
    forum
    1.02
    uploads
    1.02
    cgi
    1.00
    dp
    0.99
    photos
    0.98
    download
    0.96
    Activations Density 0.032%

    No Known Activations