© 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. 7543
    Prev
    Next
    INDEX
    Explanations

    words related to a specific location or place name, specifically "Luonono"

    oai_token-act-pair · gpt-3.5-turbo

    references to locations and notable figures associated with a specific area

    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
    amus
    -0.77
    interstitial
    -0.75
    gypt
    -0.67
     Airbus
    -0.67
     Leviathan
    -0.64
     Ashton
    -0.64
     Revis
    -0.64
     Tiger
    -0.64
    flight
    -0.64
     Kabul
    -0.63
    POSITIVE LOGITS
    ono
    2.78
     GOODMAN
    2.75
    lins
    1.68
     Rak
    1.15
    shi
    0.97
    enei
    0.87
     Fighters
    0.84
    ITNESS
    0.83
    oller
    0.82
     cooper
    0.80
    Activations Density 0.026%

    No Known Activations