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. 4-RES-JB
    6. 3558
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to working conditions and labor issues

    oai_token-act-pair · gpt-3.5-turbo

    terms related to workers and employee roles

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

    No Comments

    Negative Logits
    uits
    -1.06
    aurus
    -1.02
    cale
    -1.02
    ervatives
    -1.02
    ources
    -1.02
    pace
    -1.01
    poons
    -0.99
    mith
    -0.98
    ensical
    -0.97
    heet
    -0.96
    POSITIVE LOGITS
    holder
    0.77
    hood
    0.71
    OSP
    0.70
     pilot
    0.69
     visitation
    0.66
     VID
    0.65
    stown
    0.65
     Ally
    0.65
    less
    0.64
    craft
    0.64
    Activations Density 0.115%

    No Known Activations