© 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. 8-RES-JB
    11. 7631
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "but"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "but" indicating contrasting statements or objections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pmwiki
    -0.77
    famous
    -0.71
     Written
    -0.65
    fuck
    -0.65
    catch
    -0.62
     Merch
    -0.61
    MY
    -0.61
    ghost
    -0.60
    Purchase
    -0.59
    代
    -0.59
    POSITIVE LOGITS
     noting
    1.15
     cautioned
    1.08
     concedes
    1.03
     stressing
    1.02
     admits
    1.01
     acknowledging
    0.95
     acknowledges
    0.94
     disagreed
    0.92
     stressed
    0.91
     nonetheless
    0.91
    Activations Density 0.370%

    No Known Activations