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. 7678
    Prev
    Next
    INDEX
    Explanations

    instances of repetition or emphasis in text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "repeatedly" indicating frequent actions or behaviors

    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
    Reviewer
    -0.79
    OTA
    -0.75
    lad
    -0.74
    soc
    -0.72
    istan
    -0.72
    ocene
    -0.71
    toc
    -0.69
    rug
    -0.67
    ofi
    -0.67
    hemy
    -0.67
    POSITIVE LOGITS
    theless
    0.90
     repeated
    0.79
     reaff
    0.79
     reiter
    0.79
    è¦ļéĨĴ
    0.78
     interrupted
    0.77
     contradict
    0.77
     incarn
    0.76
    uously
    0.74
    entimes
    0.73
    Activations Density 0.023%

    No Known Activations