© 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. 1-RES-JB
    11. 1967
    Prev
    Next
    INDEX
    Explanations

    references to employees or staff in various work-related contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to employees in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    forward
    -0.77
    Pac
    -0.76
    COMPLE
    -0.75
    rous
    -0.74
    Brow
    -0.73
     horr
    -0.69
     Cause
    -0.69
     Peace
    -0.68
    ican
    -0.67
    Peace
    -0.65
    POSITIVE LOGITS
     employees
    1.06
     Employees
    0.99
     employee
    0.92
     interns
    0.85
     cafeteria
    0.83
    employ
    0.83
     workers
    0.81
    anooga
    0.80
     personnel
    0.79
     contractors
    0.77
    Activations Density 0.026%

    No Known Activations