Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 23005
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and business development

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to blockchain and digital currency technologies

    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
     blot
    -0.70
     traitor
    -0.69
     strang
    -0.66
    death
    -0.64
     faint
    -0.64
     Murder
    -0.64
     disgrace
    -0.63
     aggravated
    -0.60
     indign
    -0.59
     botched
    -0.59
    POSITIVE LOGITS
     architectures
    0.93
     innovation
    0.87
     partnerships
    0.86
     collaborations
    0.86
     technologies
    0.85
     frameworks
    0.82
     opportunities
    0.82
     capabilities
    0.82
     portfolios
    0.81
     investments
    0.81
    Activations Density 1.382%

    No Known Activations