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. 10-RES-JB
    6. 208
    Prev
    Next
    INDEX
    Explanations

    error messages instructing users to re-enter information

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to re-entering information, particularly in the context of email validation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Harmon
    -0.69
    å¥
    -0.66
    oland
    -0.64
    ãĥĵ
    -0.62
    ashtra
    -0.60
     Brah
    -0.60
    ulhu
    -0.60
     Sok
    -0.60
     Neptune
    -0.59
     sparing
    -0.59
    POSITIVE LOGITS
    enter
    0.90
    send
    0.88
    registered
    0.87
    create
    0.86
     login
    0.86
    email
    0.83
    signed
    0.82
    submit
    0.79
    apply
    0.77
    activate
    0.77
    Activations Density 0.009%

    No Known Activations