© 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. 6-RES-JB
    11. 20661
    Prev
    Next
    INDEX
    Explanations

    names of countries around the world in the format "Country name n" or "Country name followed by a number"

    oai_token-act-pair · gpt-3.5-turbo

    references to countries and geographic locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pwr
    -0.19
    catentry
    -0.18
    [_
    -0.18
    )}
    -0.18
    oÄŁan
    -0.17
    ".[
    -0.17
     [...]
    -0.17
    ).[
    -0.17
    }}}
    -0.17
    "}
    -0.17
    POSITIVE LOGITS
    ONSORED
    0.19
     understatement
    0.19
    ovember
    0.17
    iddle
    0.16
    lash
    0.16
    inness
    0.16
    viation
    0.16
    Sin
    0.15
    iaries
    0.15
     taxp
    0.15
    Activations Density 9.721%

    No Known Activations