Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10-RES-JB
    6. 22773
    Prev
    Next
    INDEX
    Explanations

    words related to employment and workplace issues, such as "employment", "workplace", and "employer"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to employment and workplace issues

    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
    quet
    -0.71
     Bundy
    -0.70
    sonian
    -0.69
     Revision
    -0.68
    opy
    -0.66
    etsk
    -0.65
    ioxide
    -0.64
    istries
    -0.64
     Oo
    -0.64
     Nanto
    -0.62
    POSITIVE LOGITS
     unions
    1.05
    employ
    0.88
     employment
    0.88
     discrimination
    0.84
    forces
    0.83
    Employ
    0.83
     union
    0.83
     ethic
    0.81
    employment
    0.80
     secretaries
    0.79
    Activations Density 0.069%

    No Known Activations