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. 19311
    Prev
    Next
    INDEX
    Explanations

    references to social media feeds

    oai_token-act-pair · gpt-3.5-turbo

    references to RSS and news feeds

    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
    istically
    -0.99
    itars
    -0.82
    pport
    -0.80
    alkyrie
    -0.74
    utory
    -0.70
    ismo
    -0.66
     POW
    -0.64
    inse
    -0.64
     bankrupt
    -0.64
     rapp
    -0.64
    POSITIVE LOGITS
     feeds
    1.10
    parser
    1.10
    feed
    1.07
    vine
    0.98
     Feed
    0.90
     feed
    0.86
    masters
    0.84
    Parser
    0.83
    Feed
    0.79
    enium
    0.78
    Activations Density 0.007%

    No Known Activations