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. 19250
    Prev
    Next
    INDEX
    Explanations

    phrases related to ongoing actions or processes

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate ongoing actions or processes

    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
    idden
    -0.79
    ranch
    -0.78
    oster
    -0.74
    onomic
    -0.74
    worker
    -0.73
    aster
    -0.72
    arta
    -0.70
    ramid
    -0.70
    ool
    -0.70
    iman
    -0.69
    POSITIVE LOGITS
     unab
    0.90
     unanswered
    0.69
     ap
    0.67
     uninterrupted
    0.66
     adolesc
    0.65
     tremend
    0.65
     momentum
    0.64
     unravel
    0.64
     unresolved
    0.64
     progressing
    0.63
    Activations Density 0.035%

    No Known Activations