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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-RES-JB
    6. 21666
    Prev
    Next
    INDEX
    Explanations

    names or terms related to the city of Charleston

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Charl."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yll
    -0.76
    iculture
    -0.69
    anship
    -0.68
    acia
    -0.68
    Äĩ
    -0.67
    yss
    -0.66
    xxxxxxxx
    -0.66
    vae
    -0.65
    prop
    -0.64
    isoft
    -0.64
    POSITIVE LOGITS
    enegger
    0.80
    limits
    0.77
     Charl
    0.73
    SpaceEngineers
    0.73
     Failure
    0.67
    soDeliveryDate
    0.67
    ogie
    0.64
     srfAttach
    0.64
    mbuds
    0.63
     Goodbye
    0.62
    Activations Density 0.001%

    No Known Activations