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. 0-RES-JB
    6. 21096
    Prev
    Next
    INDEX
    Explanations

    the word "slavery" in a historical context

    oai_token-act-pair · gpt-3.5-turbo

    the letter "k."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fixme
    -0.62
    sen
    -0.62
     fam
    -0.61
     role
    -0.61
     Unic
    -0.60
     Arn
    -0.60
     Subscribe
    -0.58
    entary
    -0.58
     TEXT
    -0.57
     voted
    -0.56
    POSITIVE LOGITS
    Pear
    0.68
    paralle
    0.68
    Ü
    0.68
    Pers
    0.67
    Helper
    0.67
    liest
    0.67
    Cho
    0.66
     Tsukuyomi
    0.65
    Failure
    0.65
    arthed
    0.64
    Activations Density 0.000%

    No Known Activations