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. 20941
    Prev
    Next
    INDEX
    Explanations

    references to formal agreements or official documents

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving the concept of "letter of intent."

    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
    adelphia
    -0.70
    ktop
    -0.64
    mone
    -0.64
    usky
    -0.62
    ials
    -0.61
    ãĤ¼ãĤ¦ãĤ¹
    -0.61
    illac
    -0.60
    é¾
    -0.60
     EntityItem
    -0.60
     externalToEVAOnly
    -0.58
    POSITIVE LOGITS
    uran
    0.72
     gratitude
    0.68
     truce
    0.65
     goodwill
    0.64
     condol
    0.62
     solidarity
    0.61
     apology
    0.60
     indictment
    0.59
     conscience
    0.59
     allegiance
    0.59
    Activations Density 0.168%

    No Known Activations