Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 13074
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and social media handles

    oai_token-act-pair · gpt-3.5-turbo

    usernames and mentions in social media context

    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
    ).[
    -0.76
    ".[
    -0.73
    ''.
    -0.72
    �
    -0.68
     Orient
    -0.66
    ."[
    -0.63
     Yug
    -0.62
     increment
    -0.62
    âĶĢâĶĢ
    -0.62
     autonom
    -0.62
    POSITIVE LOGITS
    Jr
    1.26
     @
    1.16
    _
    1.04
    FB
    1.02
     congr
    0.96
    Stud
    0.91
    official
    0.90
    why
    0.90
    john
    0.87
    HQ
    0.86
    Activations Density 0.080%

    No Known Activations