© 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. 0-RES-JB
    11. 1714
    Prev
    Next
    INDEX
    Explanations

    locations or places, especially those ending in '-erville'

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations or places, particularly 'erville' and 'vale'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EC
    -0.65
     DS
    -0.63
     overw
    -0.61
     AM
    -0.60
     inserting
    -0.59
     Dele
    -0.58
     Wonder
    -0.58
     INST
    -0.58
     overr
    -0.58
    Im
    -0.57
    POSITIVE LOGITS
    erville
    5.00
    auga
    1.66
    vale
    1.13
    ipeg
    1.12
    erness
    1.07
    atown
    1.04
    VILLE
    1.01
    olulu
    0.97
    ville
    0.93
    swick
    0.93
    Activations Density 0.018%

    No Known Activations