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. 9123
    Prev
    Next
    INDEX
    Explanations

    words related to various lifestyles

    oai_token-act-pair · gpt-3.5-turbo

    references to diverse lifestyle choices and behaviors

    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
     Released
    -0.72
    ensor
    -0.72
    gren
    -0.67
     Signed
    -0.67
    Capt
    -0.65
     Capt
    -0.65
    rar
    -0.64
    stall
    -0.63
     decrypt
    -0.62
    Error
    -0.60
    POSITIVE LOGITS
     lifestyle
    3.82
     lifestyles
    2.88
    ifestyle
    2.12
     mindset
    1.39
     diet
    1.38
     upbringing
    1.28
     wellness
    1.27
     dietary
    1.26
     habits
    1.21
     mentality
    1.19
    Activations Density 0.021%

    No Known Activations