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. 7-RES-JB
    6. 19763
    Prev
    Next
    INDEX
    Explanations

    verbs related to a decrease or disappearance over time

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to the concept of fading or diminishing

    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
    eering
    -0.69
    ortment
    -0.65
    ilda
    -0.64
    ãĤ±
    -0.63
     injection
    -0.62
     Labyrinth
    -0.60
    eport
    -0.59
    ocations
    -0.58
    square
    -0.58
     Investigative
    -0.58
    POSITIVE LOGITS
    orph
    0.83
     fade
    0.82
     belie
    0.79
    ethy
    0.77
     fades
    0.77
     abruptly
    0.75
    theless
    0.75
     violet
    0.72
    IER
    0.72
     fading
    0.72
    Activations Density 0.138%

    No Known Activations