© 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. 2947
    Prev
    Next
    INDEX
    Explanations

    phrases or names containing "Jacqu" followed by a single character

    oai_token-act-pair · gpt-3.5-turbo

    proper names, particularly of individuals and organizations

    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
    âĵĺ
    -0.83
    theless
    -0.79
     DRAG
    -0.78
    ORGE
    -0.73
    IRO
    -0.72
    AU
    -0.64
     reserve
    -0.64
    ãĤ´ãĥ³
    -0.64
     gravity
    -0.62
    ãĥĥãĤ¯
    -0.62
    POSITIVE LOGITS
    eworks
    1.25
    ership
    1.13
    isitions
    1.08
    eties
    1.05
    estones
    1.03
    emet
    1.03
    estone
    1.03
    ety
    1.01
    eme
    0.99
    igree
    0.98
    Activations Density 0.065%

    No Known Activations