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. 15016
    Prev
    Next
    INDEX
    Explanations

    words related to dedication or commitment

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "dedicate" and its variations in various contexts

    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
    HAEL
    -0.70
    è¦ļéĨĴ
    -0.67
    lain
    -0.66
     Grail
    -0.65
    picture
    -0.63
    drm
    -0.62
    ATTLE
    -0.60
     Slide
    -0.59
    Shot
    -0.59
     Ain
    -0.59
    POSITIVE LOGITS
    uced
    1.27
    ications
    1.23
    icates
    1.19
    icating
    1.12
    ication
    1.08
    ucing
    1.04
     ded
    1.01
    uces
    1.01
    icated
    1.00
    uce
    0.94
    Activations Density 0.006%

    No Known Activations