© 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. 20061
    Prev
    Next
    INDEX
    Explanations

    comparisons or contrasts indicated by the word "though"

    oai_token-act-pair · gpt-3.5-turbo

    the word "though" and its variations

    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
     exposed
    -0.65
     aligned
    -0.63
     matched
    -0.63
     available
    -0.61
     used
    -0.61
     involved
    -0.60
    lde
    -0.60
     utilized
    -0.59
     allocated
    -0.58
     radio
    -0.57
    POSITIVE LOGITS
    though
    3.77
    although
    2.43
    albeit
    1.94
    but
    1.49
     though
    1.49
    Though
    1.45
    despite
    1.37
    thought
    1.31
    unless
    1.31
    since
    1.25
    Activations Density 0.015%

    No Known Activations