Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 7401
    Prev
    Next
    INDEX
    Explanations

    phrases related to devices or products with the word "Tun" in them

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific musical or artistic entity, likely associated with "Tun" or "Tunak."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PRESS
    -0.69
     defending
    -0.64
    URE
    -0.63
    âĸĴ
    -0.61
     root
    -0.61
     probable
    -0.60
     psychotic
    -0.60
     abiding
    -0.60
     Cannabis
    -0.60
    âĸĢ
    -0.59
    POSITIVE LOGITS
    nels
    1.12
    nel
    1.10
    tun
    1.07
    eness
    1.06
     Tun
    1.03
     tun
    1.01
    aton
    1.01
    nell
    1.00
    eful
    0.94
    geon
    0.89
    Activations Density 0.006%

    No Known Activations