© 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. 7-RES-JB
    11. 2270
    Prev
    Next
    INDEX
    Explanations

    words related to facilitating or making things easier

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "facilitate" and its variations, which are associated with enabling actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    berg
    -0.76
    tal
    -0.74
    shit
    -0.70
    wig
    -0.68
    man
    -0.68
    ãĤ·ãĥ£
    -0.67
    blank
    -0.67
    tick
    -0.66
    stones
    -0.65
    mas
    -0.65
    POSITIVE LOGITS
     communication
    0.86
     conversions
    0.80
    ezvous
    0.79
     facilitating
    0.79
     transporting
    0.77
    ances
    0.77
     dissemination
    0.76
     introdu
    0.75
     transport
    0.75
     cooperation
    0.74
    Activations Density 0.058%

    No Known Activations