© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6-RES-JB
    11. 11846
    Prev
    Next
    INDEX
    Explanations

    words related to organizational units or departments within a company

    oai_token-act-pair · gpt-3.5-turbo

    references to organizational divisions or units within various entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģĦ
    -0.82
    bows
    -0.76
    天
    -0.73
     strangers
    -0.68
    çĶŁ
    -0.67
    faced
    -0.65
    ð
    -0.65
     melting
    -0.63
    rises
    -0.61
    ãĤ°
    -0.61
    POSITIVE LOGITS
    mitter
    0.81
    atics
    0.81
    eret
    0.75
    artment
    0.73
    atography
    0.72
     oversees
    0.72
    office
    0.72
    general
    0.72
    staff
    0.72
    itute
    0.72
    Activations Density 0.085%

    No Known Activations