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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RES-JB
    6. 19252
    Prev
    Next
    INDEX
    Explanations

    phrases related to email communications and newsletter subscriptions

    oai_token-act-pair · gpt-3.5-turbo

    references to email content and news updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tis
    -0.58
    Enlarge
    -0.57
     mole
    -0.56
    ifer
    -0.54
     Grants
    -0.54
    arters
    -0.54
    itans
    -0.53
     distingu
    -0.52
     Leilan
    -0.52
    alias
    -0.51
    POSITIVE LOGITS
     news
    0.80
     content
    0.72
    content
    0.68
    Content
    0.67
    EStreamFrame
    0.66
     POLITICO
    0.65
     Content
    0.64
     updates
    0.61
     personalized
    0.60
     NEWS
    0.60
    Activations Density 0.022%

    No Known Activations