© 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. 7-RES-JB
    11. 18666
    Prev
    Next
    INDEX
    Explanations

    mentions of blog posts, website links, and references to additional sources or related articles

    oai_token-act-pair · gpt-3.5-turbo

    references to online content or resources

    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
     awoke
    -0.74
     Haram
    -0.69
     transpl
    -0.64
     woke
    -0.64
    opped
    -0.62
    agonist
    -0.61
     greeted
    -0.59
     imperson
    -0.58
    onna
    -0.56
     irreversible
    -0.56
    POSITIVE LOGITS
    autions
    0.93
    FAQ
    0.84
     below
    0.82
     FAQ
    0.82
     appendix
    0.82
    ilion
    0.80
    Guide
    0.80
    below
    0.80
     wiki
    0.79
    ipedia
    0.78
    Activations Density 0.229%

    No Known Activations