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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 0-RES-JB
    6. 18
    Prev
    Next
    INDEX
    Explanations

    phrases related to ideas or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "idea"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rial
    -0.62
     laps
    -0.59
     Crimes
    -0.59
    irm
    -0.59
     Clear
    -0.58
    aba
    -0.58
    âģ
    -0.58
    qua
    -0.58
    ãĤĬ
    -0.58
    IA
    -0.57
    POSITIVE LOGITS
     idea
    3.63
     Idea
    2.39
     notion
    2.38
     ideas
    2.07
     concept
    2.03
     suggestion
    1.64
     premise
    1.57
     Ideas
    1.51
     notions
    1.49
     proposition
    1.40
    Activations Density 0.025%

    No Known Activations