© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 18445
    Prev
    Next
    INDEX
    Explanations

    instances where users are prompted to sign up for different services or newsletters

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to newsletter subscriptions and sign-up prompts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sworth
    -0.85
    ensen
    -0.73
    iuses
    -0.69
    wash
    -0.68
    isel
    -0.67
    usive
    -0.66
    hesion
    -0.65
    weak
    -0.64
     overboard
    -0.64
    oxin
    -0.64
    POSITIVE LOGITS
     Ov
    0.73
     newsletters
    0.72
     FREE
    0.71
     membership
    0.71
     updates
    0.70
     mailing
    0.67
     Membership
    0.66
     free
    0.65
     Conversation
    0.65
     email
    0.65
    Activations Density 0.041%

    No Known Activations