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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 13868
    Prev
    Next
    INDEX
    Explanations

    phrases related to promotions, offers, and deals

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to announcements or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     discredited
    -0.67
     welfare
    -0.65
     lawy
    -0.65
     coerc
    -0.63
    evidence
    -0.62
    tarian
    -0.62
     mediation
    -0.62
     unemploy
    -0.61
    elfare
    -0.61
     coercive
    -0.61
    POSITIVE LOGITS
     Featuring
    0.89
     themed
    0.81
    eaturing
    0.79
     curated
    0.75
    Fans
    0.71
     Theme
    0.71
     festive
    0.70
     showcased
    0.70
     showcases
    0.70
     premiere
    0.69
    Activations Density 1.466%

    No Known Activations