© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 10-RES-JB
    11. 1054
    Prev
    Next
    INDEX
    Explanations

    sign-up prompts for newsletters

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to newsletter subscriptions and updates

    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
    lihood
    -0.72
     Anon
    -0.68
     unaccount
    -0.63
    viation
    -0.61
     peg
    -0.58
    rendered
    -0.58
    }}}
    -0.58
     Seg
    -0.56
    ajo
    -0.56
    banks
    -0.55
    POSITIVE LOGITS
     newsletter
    0.69
    udence
    0.67
     Newsletter
    0.66
    inion
    0.65
    Balt
    0.63
    tle
    0.62
     Brief
    0.57
     shaping
    0.57
    NET
    0.57
    rive
    0.55
    Activations Density 0.039%

    No Known Activations