© 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. 10-RES-JB
    11. 1388
    Prev
    Next
    INDEX
    Explanations

    specific locations mentioned in a text

    oai_token-act-pair · gpt-3.5-turbo

    geographic locations and proper nouns related to places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilion
    -0.85
     Presidents
    -0.58
     ATM
    -0.58
     ze
    -0.57
     stagnant
    -0.57
     coffers
    -0.56
    ĵ
    -0.54
    matically
    -0.54
     cornerstone
    -0.54
    ģ«
    -0.54
    POSITIVE LOGITS
     fame
    1.52
     joins
    0.94
     whom
    0.84
     who
    0.81
     testified
    0.81
     joined
    0.81
     sidx
    0.77
    who
    0.77
    boro
    0.76
     attends
    0.76
    Activations Density 0.169%

    No Known Activations