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. 21612
    Prev
    Next
    INDEX
    Explanations

    keywords related to software development, such as "Haskell development environment", "plugin development", "Android development environment", and "SDK"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to software development

    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
    zzi
    -0.98
    Ń·
    -0.77
    cci
    -0.71
    llan
    -0.70
    Ĥİ
    -0.67
    bia
    -0.66
    idon
    -0.66
    xus
    -0.65
    zz
    -0.65
    bottom
    -0.64
    POSITIVE LOGITS
     workflow
    0.79
     kits
    0.76
     tools
    0.74
     Pione
    0.73
    smanship
    0.73
     process
    0.73
     kit
    0.72
     techniques
    0.71
    lishing
    0.71
     roadmap
    0.71
    Activations Density 0.033%

    No Known Activations