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. 4-RES-JB
    6. 18265
    Prev
    Next
    INDEX
    Explanations

    technical terms related to Drupal and circadian rhythms

    oai_token-act-pair · gpt-3.5-turbo

    references to specific software versions and technology-related terms

    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
    éĹĺ
    -0.92
     Cosponsors
    -0.87
    iour
    -0.87
    edom
    -0.82
    rawdownloadcloneembedreportprint
    -0.79
    ãĥĺ
    -0.79
    edy
    -0.78
    eele
    -0.78
    ————
    -0.77
    alties
    -0.73
    POSITIVE LOGITS
    rupal
    0.83
     Drupal
    0.82
    adian
    0.77
     Cortex
    0.74
    ĸļ
    0.73
    hift
    0.70
    agonal
    0.70
    Plex
    0.70
    ylon
    0.68
    hedral
    0.67
    Activations Density 0.024%

    No Known Activations