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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 17066
    Prev
    Next
    INDEX
    Explanations

    references to employees in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of employees in the context of organizational issues

    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
    rous
    -0.76
    Pac
    -0.75
    COMPLE
    -0.75
    Brow
    -0.73
    ican
    -0.67
     horr
    -0.67
     Peace
    -0.66
     Cause
    -0.66
    geon
    -0.65
    soon
    -0.65
    POSITIVE LOGITS
     Employees
    0.93
     employees
    0.89
     interns
    0.77
     personnel
    0.76
     employee
    0.76
     cafeteria
    0.75
     rosters
    0.71
     contractors
    0.71
     restrooms
    0.71
     Doodle
    0.70
    Activations Density 0.025%

    No Known Activations