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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 318
    Prev
    Next
    INDEX
    Explanations

    terms related to email newsletters

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to news delivery and updates

    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
    yo
    -0.78
     theoret
    -0.67
    ivas
    -0.67
    urally
    -0.66
    fitting
    -0.66
    asio
    -0.65
     Kik
    -0.65
    urat
    -0.64
    igree
    -0.63
     adm
    -0.63
    POSITIVE LOGITS
    Content
    0.81
    content
    0.79
    article
    0.74
    Brow
    0.74
     headlines
    0.73
     satire
    0.73
     alerts
    0.71
     content
    0.71
     Updates
    0.69
    Interstitial
    0.69
    Activations Density 0.073%

    No Known Activations