© 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. 6-RES-JB
    11. 3602
    Prev
    Next
    INDEX
    Explanations

    mentions of someone or something being highlighted or showcased prominently in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or works that have been highlighted or showcased

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sis
    -0.92
    alty
    -0.86
    thur
    -0.85
    ça
    -0.77
    ignt
    -0.72
    cia
    -0.68
    utral
    -0.68
    mental
    -0.66
    ersion
    -0.66
    ellig
    -0.66
    POSITIVE LOGITS
     prominently
    1.48
    Featured
    0.82
    pages
    0.75
    ãĤ´
    0.70
     featured
    0.69
     Spotlight
    0.68
     Topics
    0.67
     Featured
    0.67
     Include
    0.66
     banners
    0.65
    Activations Density 0.038%

    No Known Activations