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

    Neuronpedia

    APICircuit 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. 8737
    Prev
    Next
    INDEX
    Explanations

    terms related to the generation "Baby Boomers"

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Baby Boomer" generation

    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
    ilon
    -0.73
     geop
    -0.73
     san
    -0.68
     sworn
    -0.68
     turb
    -0.68
     homeland
    -0.67
    rm
    -0.66
    tarian
    -0.65
     pores
    -0.64
     coord
    -0.64
    POSITIVE LOGITS
     Help
    2.42
     Baby
    2.17
    Baby
    1.45
     Hearts
    1.18
    Help
    1.13
     Cue
    1.09
     Kids
    1.06
     Donation
    1.02
     HELP
    1.00
     Mama
    0.96
    Activations Density 0.021%

    No Known Activations