© 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. 0-RES-JB
    11. 1079
    Prev
    Next
    INDEX
    Explanations

    the word "merely" in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "merely" and its variants to indicate trivialization or minimizing statements

    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
     hi
    -0.61
    rain
    -0.57
     Awesome
    -0.57
     Calls
    -0.56
    Di
    -0.56
    SI
    -0.56
    ez
    -0.56
    aura
    -0.56
    oken
    -0.55
    Hi
    -0.55
    POSITIVE LOGITS
     merely
    3.23
     simply
    2.16
     mere
    1.99
     purely
    1.68
     solely
    1.59
    mere
    1.55
     strictly
    1.18
     just
    1.18
     only
    1.15
    Simply
    1.14
    Activations Density 0.007%

    No Known Activations