© 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. 2-RES-JB
    11. 12483
    Prev
    Next
    INDEX
    Explanations

    strings related to locations, especially containing the word "Worth"

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of Fort Worth and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RPG
    -0.80
    ãĥŃ
    -0.79
    é¾
    -0.77
    ãģ®å®
    -0.68
    urn
    -0.67
    ãĤ¦
    -0.67
     sol
    -0.67
    ãĥŁ
    -0.66
    ding
    -0.65
    Ts
    -0.63
    POSITIVE LOGITS
     Worth
    0.96
    Dallas
    0.79
     Aires
    0.73
    iens
    0.72
     Texans
    0.71
    ciating
    0.70
     Mavericks
    0.70
    lington
    0.70
     Lauderdale
    0.68
    ampa
    0.68
    Activations Density 0.009%

    No Known Activations