© 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. 11-RES-JB
    11. 23126
    Prev
    Next
    INDEX
    Explanations

    locations or geographical features

    oai_token-act-pair · gpt-3.5-turbo

    geographical features and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mates
    -0.77
    acters
    -0.77
     listeners
    -0.74
     audiences
    -0.71
     DJs
    -0.70
     diapers
    -0.70
    emort
    -0.70
     classrooms
    -0.70
    humans
    -0.70
     weddings
    -0.69
    POSITIVE LOGITS
     River
    1.58
     Mountains
    1.44
     river
    1.42
     coastline
    1.28
     Strait
    1.25
     Basin
    1.19
     rivers
    1.19
     basin
    1.19
     Peninsula
    1.18
     Corridor
    1.17
    Activations Density 0.236%

    No Known Activations