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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 3-RES-JB
    6. 2076
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific location, possibly a town or point called "Whiskey."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations or geographic places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DEFENSE
    -0.71
     ABE
    -0.68
    eering
    -0.64
    ļéĨĴ
    -0.63
     traps
    -0.62
    alian
    -0.62
     mileage
    -0.62
     concessions
    -0.61
     Factor
    -0.60
     Opera
    -0.60
    POSITIVE LOGITS
    ppers
    1.12
    ple
    1.06
    pper
    1.05
    ven
    1.00
    pped
    0.98
    pe
    0.89
    pling
    0.88
    plets
    0.87
    pes
    0.86
    cil
    0.85
    Activations Density 0.028%

    No Known Activations