© 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. 8-RES-JB
    11. 7986
    Prev
    Next
    INDEX
    Explanations

    verbs ending in '-ing' with a focus on actions or processes

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and words indicating ongoing or continuous actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CRE
    -0.63
    VID
    -0.62
    Lear
    -0.62
    spot
    -0.61
    ushi
    -0.60
    REL
    -0.60
    Spons
    -0.59
    Specific
    -0.59
     Guerrero
    -0.59
     Sitting
    -0.59
    POSITIVE LOGITS
     mechanism
    1.00
     process
    0.98
     algorithm
    0.88
     scheme
    0.85
     procedure
    0.83
    xual
    0.82
     effect
    0.80
     technique
    0.78
     thereof
    0.78
     mechanisms
    0.77
    Activations Density 0.277%

    No Known Activations