© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 24084
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to occupation or occupation-related activities

    oai_token-act-pair · gpt-3.5-turbo

    terminology and references related to occupation and occupation-related activities

    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
    HER
    -0.74
    bite
    -0.72
    ministic
    -0.66
    20439
    -0.65
     Birch
    -0.65
    hammad
    -0.64
     rendition
    -0.63
    jee
    -0.63
    frog
    -0.63
     pear
    -0.62
    POSITIVE LOGITS
    itions
    0.89
    ational
    0.85
     Occup
    0.85
    Occup
    0.80
    rovers
    0.78
    estate
    0.76
    ographs
    0.73
    ynski
    0.72
    iers
    0.71
     Occupations
    0.70
    Activations Density 0.018%

    No Known Activations