© 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. 4-RES-JB
    11. 15268
    Prev
    Next
    INDEX
    Explanations

    adjectives or verbs related to being efficient or slender in physical appearance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "lean" in various contexts

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

    No Comments

    Negative Logits
    displayText
    -0.77
    ilage
    -0.75
    uber
    -0.71
     NOTICE
    -0.71
     Ukrain
    -0.71
    protected
    -0.70
    illon
    -0.68
    ãĤ»
    -0.68
    vous
    -0.67
     Dresden
    -0.67
    POSITIVE LOGITS
     lean
    1.02
    lean
    0.90
    Lean
    0.89
    ings
    0.79
    ener
    0.77
     shoulders
    0.77
    erness
    0.77
     leaning
    0.76
     Lean
    0.76
    rients
    0.75
    Activations Density 0.011%

    No Known Activations