© 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. 9232
    Prev
    Next
    INDEX
    Explanations

    instances of people being hired for various roles or positions

    oai_token-act-pair · gpt-3.5-turbo

    the word "hired" and related concepts of employment

    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
    ican
    -0.78
    eq
    -0.76
    idem
    -0.73
    que
    -0.69
    atomic
    -0.67
    alone
    -0.67
    psey
    -0.67
    jer
    -0.66
    itous
    -0.66
    edly
    -0.65
    POSITIVE LOGITS
     hired
    1.07
     hire
    0.98
    glers
    0.91
     hires
    0.83
     assistants
    0.81
     hiring
    0.79
     Dame
    0.78
     mercenaries
    0.76
    lasses
    0.76
    ãĥ¼ãĥĨ
    0.73
    Activations Density 0.015%

    No Known Activations