© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 16009
    Prev
    Next
    INDEX
    Explanations

    phrases related to business operations and procedures

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of collective ownership or belonging

    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
    icter
    -0.94
    edi
    -0.83
    */(
    -0.75
    cum
    -0.72
    izu
    -0.72
    yang
    -0.71
    puff
    -0.70
    wrap
    -0.69
    oldemort
    -0.69
    conom
    -0.68
    POSITIVE LOGITS
    selves
    1.15
     own
    1.08
     customers
    1.04
     partners
    1.04
     clients
    1.02
     competitors
    0.96
     ourselves
    0.92
     mission
    0.92
     affiliates
    0.92
     guests
    0.89
    Activations Density 0.137%

    No Known Activations