© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 16860
    Prev
    Next
    INDEX
    Explanations

    mentions of lifestyles

    oai_token-act-pair · gpt-3.5-turbo

    terms related to lifestyle choices and variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rations
    -0.86
    opening
    -0.68
    essee
    -0.68
    ħ
    -0.64
    drawn
    -0.64
    astern
    -0.62
    arching
    -0.62
    supp
    -0.61
    ough
    -0.61
    phabet
    -0.60
    POSITIVE LOGITS
     lifestyle
    1.19
     lifestyles
    1.10
    ifestyle
    0.92
     advoc
    0.83
     habits
    0.80
    orously
    0.79
     experien
    0.72
     challeng
    0.71
     arrang
    0.70
     behaviours
    0.69
    Activations Density 0.006%

    No Known Activations