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. 10329
    Prev
    Next
    INDEX
    Explanations

    mentions of corporate actions like closures, layoffs, and relocations

    oai_token-act-pair · gpt-3.5-turbo

    financial details regarding business operations

    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
    ertodd
    -0.74
     Explan
    -0.74
    cussion
    -0.71
    ecd
    -0.71
    Aid
    -0.70
     shaming
    -0.70
    eches
    -0.69
    Spoiler
    -0.67
    oros
    -0.66
    ukong
    -0.66
    POSITIVE LOGITS
     headquarters
    1.44
     offices
    1.28
     subsidiaries
    1.26
     operations
    1.23
     branches
    1.13
     stores
    1.12
     locations
    1.10
     warehouses
    1.05
     subsidiary
    1.04
     affiliates
    1.04
    Activations Density 0.451%

    No Known Activations