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. 11-RES-JB
    6. 15788
    Prev
    Next
    INDEX
    Explanations

    phrases related to large amounts of money

    oai_token-act-pair · gpt-3.5-turbo

    references to multi-faceted or multi-layered aspects of topics or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     preced
    -0.75
     AVG
    -0.69
     Lans
    -0.68
     precedence
    -0.68
     Boxing
    -0.67
     onward
    -0.66
     absent
    -0.66
     alone
    -0.65
     skim
    -0.64
     Rab
    -0.64
    POSITIVE LOGITS
    dimensional
    1.55
    billion
    1.53
    million
    1.53
    purpose
    1.52
    disciplinary
    1.52
    ethnic
    1.48
    racial
    1.43
    functional
    1.38
    colored
    1.36
    cultural
    1.34
    Activations Density 0.020%

    No Known Activations