Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 12535
    Prev
    Next
    INDEX
    Explanations

    phrases related to information or knowledge

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to environmental concerns and potential risks

    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
     ______
    -0.63
     Dealer
    -0.58
     Shotgun
    -0.55
     OpenGL
    -0.54
     hills
    -0.53
     assassinated
    -0.52
     Tavern
    -0.52
    ĪĴ
    -0.52
     Hist
    -0.51
     TED
    -0.51
    POSITIVE LOGITS
    UF
    0.65
    glers
    0.63
    operation
    0.63
    igil
    0.62
    cture
    0.62
     prank
    0.59
    ãĤ¼ãĤ¦ãĤ¹
    0.59
    efe
    0.59
     hotline
    0.58
    ulent
    0.58
    Activations Density 1.281%

    No Known Activations