© 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. 23041
    Prev
    Next
    INDEX
    Explanations

    words related to proper nouns or names

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the substring "les" in various contexts

    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
    raviolet
    -0.81
    oÄŁ
    -0.72
     citiz
    -0.68
    tains
    -0.67
     Seym
    -0.66
     pund
    -0.65
    rador
    -0.64
    yrinth
    -0.64
     carbohyd
    -0.63
    ĻĤ
    -0.60
    POSITIVE LOGITS
    bury
    1.18
    hip
    1.11
    bians
    1.06
    pace
    1.02
    hots
    1.01
    bian
    1.01
    ville
    0.99
    creen
    0.99
    burg
    0.98
    worth
    0.95
    Activations Density 0.013%

    No Known Activations