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. 23350
    Prev
    Next
    INDEX
    Explanations

    mentions of specific operating systems and software versions

    oai_token-act-pair · gpt-3.5-turbo

    references to Windows 10 and its features or 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
    rahim
    -0.90
    rang
    -0.82
    govtrack
    -0.79
    href
    -0.74
     jug
    -0.72
    iosyncr
    -0.71
    rious
    -0.71
    usra
    -0.70
    zl
    -0.69
     Huss
    -0.67
    POSITIVE LOGITS
     Insider
    0.80
     Anniversary
    0.79
    Ħ¢
    0.78
     SSD
    0.77
    bourg
    0.75
     Linux
    0.74
     IoT
    0.74
    Linux
    0.74
     2050
    0.72
     Creat
    0.71
    Activations Density 0.038%

    No Known Activations