© 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. 6-RES-JB
    11. 14844
    Prev
    Next
    INDEX
    Explanations

    comparisons or similes using the word "like"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "like" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ascript
    -0.77
    enhagen
    -0.76
    abases
    -0.75
    Language
    -0.72
    alt
    -0.71
    merce
    -0.70
    otiation
    -0.70
    igion
    -0.70
    inion
    -0.69
    alez
    -0.68
    POSITIVE LOGITS
    lier
    0.81
    liest
    0.74
    lihood
    0.71
     quaint
    0.71
     chatter
    0.69
     dé
    0.67
     straightforward
    0.63
    ¥µ
    0.62
     spam
    0.62
     innocuous
    0.62
    Activations Density 0.023%

    No Known Activations