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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 5-RES-JB
    6. 23696
    Prev
    Next
    INDEX
    Explanations

    code-related keywords such as "import," "Control," and "url."

    oai_token-act-pair · gpt-3.5-turbo

    keywords and phrases related to programming, specifically about control methods and import functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.87
     UFOs
    -0.79
    aith
    -0.70
     Horus
    -0.70
    jri
    -0.69
    seys
    -0.65
    eff
    -0.65
    sic
    -0.64
     EVs
    -0.64
     streaks
    -0.64
    POSITIVE LOGITS
     namespace
    0.82
    Input
    0.81
     isEnabled
    0.81
    utils
    0.81
    Resource
    0.76
     alloc
    0.73
    Parser
    0.72
     import
    0.72
    plugin
    0.71
    Initial
    0.71
    Activations Density 0.088%

    No Known Activations