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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 3557
    Prev
    Next
    INDEX
    Explanations

    instances of frequency and repetition

    oai_token-act-pair · gpt-3.5-turbo

    adverbs that describe frequency or manner of occurrence

    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
    ves
    -0.77
    utenberg
    -0.73
    inea
    -0.72
    iry
    -0.68
    isf
    -0.68
    own
    -0.68
    pires
    -0.68
    itivity
    -0.68
    vae
    -0.67
     Clicker
    -0.67
    POSITIVE LOGITS
     preferring
    0.86
     excluding
    0.85
     preferably
    0.79
    entimes
    0.77
    christ
    0.77
     comprising
    0.77
     implying
    0.75
     adolesc
    0.75
     consisting
    0.73
     noting
    0.73
    Activations Density 0.192%

    No Known Activations