Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 17587
    Prev
    Next
    INDEX
    Explanations

    specifically the country "Italy."

    oai_token-act-pair · gpt-3.5-turbo

    references to Italy and Italian-related terms

    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
    \\\\\\\\
    -0.99
    bilt
    -0.91
    tick
    -0.89
    TPPStreamerBot
    -0.89
    lasses
    -0.85
    holder
    -0.84
    pir
    -0.84
    ridges
    -0.82
    ciating
    -0.80
    soDeliveryDate
    -0.79
    POSITIVE LOGITS
     Fasc
    0.83
     Renaissance
    0.82
     Alps
    0.82
    otti
    0.81
     Inquisition
    0.81
     Serie
    0.78
    etta
    0.77
     Sicily
    0.77
    igne
    0.77
     Italy
    0.76
    Activations Density 0.036%

    No Known Activations