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. 16329
    Prev
    Next
    INDEX
    Explanations

    introductory phrases or statements, e.g., "First and foremost," "First thing," or "Things first."

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the importance of things or ideas

    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
    interrupted
    -0.76
    ynt
    -0.68
     unfocusedRange
    -0.65
     insecure
    -0.63
    ingen
    -0.63
    Spoiler
    -0.63
    abled
    -0.63
    ulkan
    -0.62
    ween
    -0.61
    ancies
    -0.61
    POSITIVE LOGITS
    edly
    0.74
     Rouhani
    0.72
     Misty
    0.72
     foremost
    0.72
    imester
    0.71
     volley
    0.70
     introdu
    0.66
    eve
    0.63
     Alexa
    0.63
     Nev
    0.62
    Activations Density 0.191%

    No Known Activations