© 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. 16756
    Prev
    Next
    INDEX
    Explanations

    phrases indicating strong assertions or demands

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "insist" or its variations in different contexts

    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
     Level
    -0.63
     trough
    -0.58
     type
    -0.57
     Hearthstone
    -0.57
     impacts
    -0.57
     Cause
    -0.57
     crossover
    -0.56
     cross
    -0.56
     ranges
    -0.56
     portion
    -0.56
    POSITIVE LOGITS
     insist
    2.74
     insisted
    2.71
     insists
    2.53
     insisting
    2.36
     insistence
    2.01
     adamant
    1.50
     refused
    1.35
     refuses
    1.35
     demanded
    1.31
     balk
    1.20
    Activations Density 0.030%

    No Known Activations