© 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. 3-RES-JB
    11. 3209
    Prev
    Next
    INDEX
    Explanations

    comparative terms indicating the relationship or comparison between different things or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to relative comparisons or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    spr
    -1.00
    ERG
    -0.89
    mberg
    -0.86
    iere
    -0.82
    storm
    -0.82
    eret
    -0.80
    ̶
    -0.79
    immer
    -0.77
    λ
    -0.74
    stra
    -0.73
    POSITIVE LOGITS
     humidity
    0.99
     pressures
    0.80
     newcomer
    0.79
     ease
    0.79
     pronoun
    0.78
     autonomy
    0.76
     pronouns
    0.74
     newcom
    0.73
     abund
    0.72
     uncle
    0.71
    Activations Density 0.008%

    No Known Activations