© 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. 8-RES-JB
    11. 17634
    Prev
    Next
    INDEX
    Explanations

    prepositions and phrases indicating a comparison between two things

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "on the one hand" and its variations, indicating contrasts or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lessly
    -0.69
    ties
    -0.62
    stein
    -0.61
    wine
    -0.61
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.61
     someday
    -0.61
    LOCK
    -0.60
    ruciating
    -0.60
    beard
    -0.60
    tre
    -0.59
    POSITIVE LOGITS
     occasion
    1.14
     heels
    1.12
     occasions
    1.08
     downside
    1.06
     contrary
    1.06
     basis
    1.02
     periphery
    0.98
     verge
    0.91
     eve
    0.88
     outskirts
    0.87
    Activations Density 0.075%

    No Known Activations