© 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. 5085
    Prev
    Next
    INDEX
    Explanations

    proper nouns specifically related to individuals named "Leroux" and a particular term related to "Monster 7"

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to specific characters or entities, particularly those associated with the term "Monster."

    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
    Labor
    -0.80
     Recomm
    -0.76
     Tend
    -0.72
     Spart
    -0.70
     legion
    -0.70
     Democr
    -0.69
    comm
    -0.69
     Consent
    -0.68
     Committees
    -0.67
     Govern
    -0.66
    POSITIVE LOGITS
    oux
    2.51
     Monster
    2.11
    Monster
    1.33
     ICE
    1.00
     batter
    0.99
     dessert
    0.99
     pudding
    0.96
     Ellis
    0.90
    otte
    0.81
     cust
    0.80
    Activations Density 0.019%

    No Known Activations