© 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. 9-RES-JB
    11. 1331
    Prev
    Next
    INDEX
    Explanations

    digits often associated with video or audio content

    oai_token-act-pair · gpt-3.5-turbo

    references to multimedia content types and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Canaver
    -0.99
     Tsarnaev
    -0.85
     Scalia
    -0.82
     Abedin
    -0.77
     Grassley
    -0.76
     Pruitt
    -0.76
     Krugman
    -0.75
     Gutenberg
    -0.73
     Manafort
    -0.72
     Mulcair
    -0.72
    POSITIVE LOGITS
    Interstitial
    0.83
     facebook
    0.75
     trave
    0.73
     livest
    0.71
     helicop
    0.63
     english
    0.61
     whilst
    0.60
     Youtube
    0.60
     HOT
    0.57
     Whilst
    0.57
    Activations Density 1.830%

    No Known Activations