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. 11-RES-JB
    6. 18271
    Prev
    Next
    INDEX
    Explanations

    keywords related to financial assets

    oai_token-act-pair · gpt-3.5-turbo

    references to assets and asset management concepts

    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
    bone
    -0.80
    gaard
    -0.78
     Grounds
    -0.75
    apers
    -0.72
    DAY
    -0.69
    bling
    -0.68
    geon
    -0.68
    tons
    -0.68
    bowl
    -0.67
    dor
    -0.67
    POSITIVE LOGITS
     forfeiture
    1.25
     holdings
    1.11
     asset
    0.98
     seizure
    0.97
     allocation
    0.96
     forfe
    0.91
     freezes
    0.87
     accumulation
    0.83
     seizures
    0.83
    iture
    0.83
    Activations Density 0.036%

    No Known Activations