© 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. 1-RES-JB
    11. 7076
    Prev
    Next
    INDEX
    Explanations

    places or entities related to the word "Rome"

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of Rome and medical or clinical terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ILCS
    -0.83
    picking
    -0.78
    ERA
    -0.76
    ippers
    -0.72
     calcul
    -0.72
     convol
    -0.72
    opian
    -0.71
     facult
    -0.70
    renheit
    -0.69
     informants
    -0.68
    POSITIVE LOGITS
    rome
    1.30
    ographed
    0.79
     Mehran
    0.79
    Org
    0.76
    agle
    0.76
    Reloaded
    0.75
    code
    0.74
    REDACTED
    0.74
    *****
    0.74
     Roc
    0.73
    Activations Density 0.025%

    No Known Activations