© 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. 2951
    Prev
    Next
    INDEX
    Explanations

    words related to collaboration or cooperation, specifically with the prefix "co-"

    oai_token-act-pair · gpt-3.5-turbo

    references to coworkers and teamwork

    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
    lihood
    -0.71
    ĪĴ
    -0.70
     Brah
    -0.69
     Sorce
    -0.67
     Galileo
    -0.65
     Thin
    -0.65
     nort
    -0.64
     AVG
    -0.64
     Hawth
    -0.64
    ¥µ
    -0.63
    POSITIVE LOGITS
    branded
    1.16
    authored
    1.13
    founder
    1.13
    signed
    1.10
    operative
    1.07
    ordinate
    1.06
    cil
    1.04
    interstitial
    1.04
    operated
    1.01
    development
    0.99
    Activations Density 0.032%

    No Known Activations