© 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. 9-RES-JB
    11. 15540
    Prev
    Next
    INDEX
    Explanations

    Proper nouns and entities such as names of companies, people, and places

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to companies, organizations, or people's names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izoph
    -0.78
    âĶĢâĶĢâĶĢâĶĢ
    -0.74
    ãĤ¤ãĥĪ
    -0.73
    Ò
    -0.69
    ĺħ
    -0.69
    worldly
    -0.67
    ̶
    -0.65
    7601
    -0.64
    ãĤ¦ãĤ¹
    -0.63
    Ùħ
    -0.62
    POSITIVE LOGITS
     meanwhile
    1.37
     declined
    1.31
     spokesman
    1.29
     spokeswoman
    1.28
     also
    1.23
     denies
    1.11
     appealed
    1.07
     insists
    1.06
     responded
    1.04
     acknowledges
    1.02
    Activations Density 0.749%

    No Known Activations