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. 2-RES-JB
    6. 9197
    Prev
    Next
    INDEX
    Explanations

    mentions of things being formally or officially ordered or mandated

    oai_token-act-pair · gpt-3.5-turbo

    references to hierarchical arrangements or sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tek
    -0.86
    sters
    -0.83
    mist
    -0.81
    ster
    -0.79
    bread
    -0.75
    igans
    -0.75
    shop
    -0.74
    ighty
    -0.71
    eworks
    -0.71
    istered
    -0.70
    POSITIVE LOGITS
    Magikarp
    0.78
    OPLE
    0.75
    Ô
    0.74
    âĸĪâĸĪâĸĪâĸĪ
    0.74
    âĸĪâĸĪ
    0.73
    ipolar
    0.71
    Constructed
    0.71
    ordering
    0.69
    Ò
    0.69
    CONT
    0.68
    Activations Density 0.035%

    No Known Activations