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. 13514
    Prev
    Next
    INDEX
    Explanations

    mentions of "one" with a high importance or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating singular entities or unique occurrences

    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
    inity
    -0.67
    ooks
    -0.67
    gif
    -0.67
    ories
    -0.66
     warranties
    -0.61
    respective
    -0.61
     Vaugh
    -0.60
     galleries
    -0.60
    ãĤµ
    -0.60
    older
    -0.59
    POSITIVE LOGITS
     hundred
    0.98
     Hundred
    0.89
    esan
    0.83
     sided
    0.82
     dimensional
    0.81
     thousand
    0.79
     Piece
    0.77
     thing
    0.76
     crore
    0.74
     month
    0.73
    Activations Density 0.075%

    No Known Activations