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. 0-RES-JB
    6. 5476
    Prev
    Next
    INDEX
    Explanations

    the word "Meanwhile."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Meanwhile."

    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
     simple
    -0.70
     pred
    -0.68
     origin
    -0.65
     defin
    -0.65
     rule
    -0.63
     defined
    -0.63
     common
    -0.62
     defining
    -0.61
     initials
    -0.60
     term
    -0.60
    POSITIVE LOGITS
     Meanwhile
    3.24
    Meanwhile
    2.54
    anwhile
    2.02
     meanwhile
    1.68
    Elsewhere
    1.50
     Conversely
    1.49
     Similarly
    1.48
     Eventually
    1.44
     Likewise
    1.43
     Finally
    1.41
    Activations Density 0.016%

    No Known Activations