© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2276
    Prev
    Next
    INDEX
    Explanations

    preceding clauses that contrast with or provide context for subsequent statements

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "Although" to introduce contrasting 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
     tomorrow
    -0.77
     stuff
    -0.67
     shit
    -0.67
     part
    -0.67
     lands
    -0.66
     yours
    -0.65
     your
    -0.65
     back
    -0.65
     better
    -0.64
     civ
    -0.64
    POSITIVE LOGITS
     Although
    2.58
    Although
    2.40
     Though
    2.08
    Though
    1.85
     Despite
    1.76
    although
    1.71
     Whilst
    1.71
     However
    1.70
    Despite
    1.64
     Nevertheless
    1.62
    Activations Density 0.020%

    No Known Activations