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. 10-RES-JB
    6. 11015
    Prev
    Next
    INDEX
    Explanations

    proper names of individuals, likely related to news or legal contexts

    oai_token-act-pair · gpt-3.5-turbo

    proper names of individuals, particularly in a legal or official context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enrollment
    -0.91
     honoring
    -0.90
     modernization
    -0.87
    Hispanic
    -0.87
     honor
    -0.86
     flavors
    -0.84
     offense
    -0.83
     tumors
    -0.82
     favorable
    -0.79
     unfavorable
    -0.78
    POSITIVE LOGITS
     Davies
    1.35
     Cardiff
    1.23
     Fraser
    1.23
     Downing
    1.20
     Corbyn
    1.20
     Welsh
    1.18
     Pearce
    1.17
     Atkinson
    1.16
     Sutton
    1.15
     Wilkinson
    1.13
    Activations Density 0.221%

    No Known Activations