© 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. 11257
    Prev
    Next
    INDEX
    Explanations

    the prefix "con-" repeated before different suffixes

    oai_token-act-pair · gpt-3.5-turbo

    words or prefixes related to concepts of agreement or consensus

    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
    terday
    -0.77
    TPS
    -0.74
     Norn
    -0.72
    baugh
    -0.71
    HAEL
    -0.70
    ewski
    -0.68
     Decay
    -0.63
    assetsadobe
    -0.62
    ¶ħ
    -0.60
    ACK
    -0.60
    POSITIVE LOGITS
    clusively
    1.04
    gru
    1.00
    venient
    0.95
    formance
    0.95
    clave
    0.95
    naissance
    0.94
    nex
    0.93
    gres
    0.90
    formation
    0.88
    ventions
    0.88
    Activations Density 0.010%

    No Known Activations