© 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. 4-RES-JB
    11. 23697
    Prev
    Next
    INDEX
    Explanations

    words related to factories and production processes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "factory" in various contexts related to industrial production and agriculture

    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
    laus
    -0.91
    soever
    -0.83
    byss
    -0.73
    lihood
    -0.71
    vind
    -0.69
    partisan
    -0.67
    ĺħ
    -0.67
    thood
    -0.66
    */(
    -0.66
    eeper
    -0.65
    POSITIVE LOGITS
    actory
    0.91
     factory
    0.89
    Made
    0.77
    ounter
    0.76
     farming
    0.75
     worker
    0.74
    orer
    0.73
     Worker
    0.73
    worker
    0.73
    rats
    0.70
    Activations Density 0.012%

    No Known Activations