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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 3638
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "want" and related expressions of desire or choice

    oai_token-act-pair · gpt-3.5-turbo

    expressions of freedom and choice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ļéĨĴ
    -0.76
    sha
    -0.62
     Immunity
    -0.60
     Annotations
    -0.59
    EStreamFrame
    -0.57
    dust
    -0.55
     Trilogy
    -0.55
    livious
    -0.55
     Andersen
    -0.55
     Imm
    -0.54
    POSITIVE LOGITS
     desired
    1.19
     pleased
    1.14
    want
    1.12
     want
    1.09
     desire
    1.08
     wished
    1.05
     ple
    1.05
     liking
    1.05
     wish
    1.03
     wills
    1.02
    Activations Density 0.163%

    No Known Activations