© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11124
    Prev
    Next
    INDEX
    Explanations

    words related to geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    geographic locations and their relationships or characteristics

    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
     modifying
    -0.72
    Lear
    -0.72
    isner
    -0.67
     saying
    -0.65
     incremental
    -0.64
     recommending
    -0.64
     substit
    -0.62
     undermining
    -0.62
     suggestions
    -0.62
    andowski
    -0.62
    POSITIVE LOGITS
     encompasses
    1.21
     borders
    1.19
     belongs
    1.17
    population
    1.15
     contains
    1.11
     comprises
    1.10
     belonged
    1.10
     sits
    1.09
     occupies
    1.07
     boasts
    1.05
    Activations Density 0.304%

    No Known Activations