© 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. 6869
    Prev
    Next
    INDEX
    Explanations

    links or prompts for subscribing to newsletters

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to subscription offers for newsletters and updates

    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
    aukee
    -0.78
    hya
    -0.71
     tentacles
    -0.68
     depiction
    -0.64
    cule
    -0.64
    channelAvailability
    -0.64
     casing
    -0.64
     condu
    -0.64
     shading
    -0.63
    ../
    -0.63
    POSITIVE LOGITS
     newsletter
    0.85
     Newsletter
    0.85
     Updates
    0.84
     ARTICLE
    0.79
    Subscribe
    0.71
     Podcast
    0.71
     Subscribe
    0.70
     iTunes
    0.69
     newsletters
    0.69
    Newsletter
    0.69
    Activations Density 0.071%

    No Known Activations