Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 17247
    Prev
    Next
    INDEX
    Explanations

    short phrases with "Meanwhile," signaling a shift in focus or events happening at the same time

    oai_token-act-pair · gpt-3.5-turbo

    the word "Meanwhile" and its frequency within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¯ãĥ³
    -0.89
    frac
    -0.79
    viation
    -0.79
    QB
    -0.75
    ãĥĥãĥī
    -0.75
    iken
    -0.73
    apest
    -0.70
    ãĥĺãĥ©
    -0.69
    ãĥİ
    -0.69
    ãĥ´
    -0.68
    POSITIVE LOGITS
     meanwhile
    0.87
     elsewhere
    0.79
     another
    0.79
     however
    0.74
     commentators
    0.69
     proponents
    0.69
     others
    0.68
     tensions
    0.67
     environmentalists
    0.65
     there
    0.64
    Activations Density 0.129%

    No Known Activations