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. 19258
    Prev
    Next
    INDEX
    Explanations

    references to the term "Dam" or variations thereof

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Damon Lindelof

    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
    avorite
    -0.82
     syrup
    -0.68
     Subtle
    -0.66
     Hawaiian
    -0.66
     Garner
    -0.65
     profiling
    -0.65
    ģĸ
    -0.64
     retail
    -0.61
     firearms
    -0.61
     sugars
    -0.60
    POSITIVE LOGITS
    ukong
    1.08
    ned
    0.91
    nation
    0.89
    mit
    0.86
    vid
    0.86
    ascus
    0.85
    iour
    0.85
    iac
    0.82
    amaz
    0.81
    iani
    0.81
    Activations Density 0.011%

    No Known Activations