© 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. 10-RES-JB
    11. 20226
    Prev
    Next
    INDEX
    Explanations

    mentions of podcasts and blog posts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to announcements or 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
    fman
    -0.80
    kefeller
    -0.79
    cult
    -0.75
     rhet
    -0.74
    SPONSORED
    -0.72
    âĵĺ
    -0.68
     antit
    -0.65
    cart
    -0.65
    onyms
    -0.64
     believable
    -0.64
    POSITIVE LOGITS
     hiatus
    1.02
     ðŁĻĤ
    1.02
    iatus
    1.00
     holidays
    0.91
     Patreon
    0.90
     THANK
    0.89
     Updates
    0.86
     busy
    0.85
     update
    0.83
     recap
    0.82
    Activations Density 0.635%

    No Known Activations