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. 994
    Prev
    Next
    INDEX
    Explanations

    references to the city of Charlotte

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of Charlotte

    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
    hig
    -0.77
    egal
    -0.75
    arial
    -0.71
    culosis
    -0.69
    Soviet
    -0.67
    kaya
    -0.66
     indo
    -0.65
    algia
    -0.65
    ebin
    -0.64
    lying
    -0.64
    POSITIVE LOGITS
    otte
    1.21
     Hornets
    1.15
    sburg
    1.06
     Charlotte
    1.04
     Raleigh
    0.93
    ottesville
    0.92
     Observer
    0.84
    burg
    0.83
     Wilmington
    0.83
    boro
    0.81
    Activations Density 0.008%

    No Known Activations