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. 6-RES-JB
    6. 20869
    Prev
    Next
    INDEX
    Explanations

    mentions of the city of Miami

    oai_token-act-pair · gpt-3.5-turbo

    the city name "Miami" in various contexts

    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
     guiActiveUn
    -0.86
    uably
    -0.81
    UGC
    -0.81
    ebook
    -0.81
    sed
    -0.76
    iary
    -0.74
    rd
    -0.73
    onomic
    -0.73
    uers
    -0.72
    Els
    -0.71
    POSITIVE LOGITS
     Beach
    1.16
     Gardens
    1.14
     Dolphins
    1.11
     Marlins
    1.00
     Hurricanes
    0.97
     Heat
    0.96
    ricanes
    0.88
     Herald
    0.84
     Harbour
    0.83
     Lakes
    0.79
    Activations Density 0.017%

    No Known Activations