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. 1719
    Prev
    Next
    INDEX
    Explanations

    official orders being given or instructions being issued

    oai_token-act-pair · gpt-3.5-turbo

    commands or orders issued by authority figures

    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
    nown
    -0.81
    touch
    -0.70
    olate
    -0.69
    jri
    -0.68
     chances
    -0.65
    anch
    -0.64
     touched
    -0.63
     Lenn
    -0.63
    craft
    -0.62
    nces
    -0.62
    POSITIVE LOGITS
     destruction
    0.80
     removal
    0.77
     deportation
    0.76
     demolition
    0.76
     cancellation
    0.75
     evacuation
    0.74
     reconsider
    0.72
     inquiry
    0.72
    RECT
    0.71
     renewal
    0.71
    Activations Density 0.129%

    No Known Activations