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. 0-RES-JB
    6. 23491
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific person named Friedman

    oai_token-act-pair · gpt-3.5-turbo

    references to the economist Milton Friedman and related discussions

    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
     wo
    -0.84
    dragon
    -0.79
     apr
    -0.76
     woodland
    -0.76
     lvl
    -0.75
     hop
    -0.75
     turtle
    -0.74
     armour
    -0.74
    Miss
    -0.73
     burnt
    -0.73
    POSITIVE LOGITS
     Friedman
    2.86
     Goldstein
    2.44
     Greenberg
    2.41
     Shapiro
    2.36
     Goldberg
    2.25
     Levine
    2.23
     Rubin
    2.21
     Lieberman
    2.19
     Berman
    2.19
     Feldman
    2.18
    Activations Density 0.047%

    No Known Activations