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. 9-RES-JB
    6. 19012
    Prev
    Next
    INDEX
    Explanations

    words related to work, including its various aspects such as work-life balance, work-related stress, and work-related migrations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to work and employment issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Vote
    -0.69
    etsk
    -0.69
    dot
    -0.68
    oller
    -0.62
     thunder
    -0.59
     Jays
    -0.58
    reme
    -0.56
    ricular
    -0.56
     vault
    -0.56
    Jump
    -0.55
    POSITIVE LOGITS
    weeney
    0.64
     Macron
    0.63
     Progress
    0.63
    ause
    0.63
    umbered
    0.59
    ardo
    0.59
    Progress
    0.58
    ontent
    0.58
    enment
    0.58
     diligence
    0.58
    Activations Density 0.215%

    No Known Activations