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. 6274
    Prev
    Next
    INDEX
    Explanations

    personal pronouns followed by strong confidence or certainty statements

    oai_token-act-pair · gpt-3.5-turbo

    the first-person and third-person pronouns indicating personal and collective experiences

    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
    stellar
    -0.79
     Globe
    -0.77
    eworthy
    -0.76
     Hague
    -0.71
     Confederation
    -0.66
    odder
    -0.62
     Leban
    -0.62
     Akron
    -0.61
    amia
    -0.61
     Yel
    -0.61
    POSITIVE LOGITS
    'll
    1.10
    've
    1.05
    'd
    0.99
    're
    0.98
     could
    0.82
     intend
    0.79
     owe
    0.79
    'm
    0.77
     shouldn
    0.77
    ould
    0.76
    Activations Density 0.251%

    No Known Activations