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. 0-RES-JB
    6. 21009
    Prev
    Next
    INDEX
    Explanations

    words related to necessity and requirement

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the importance of necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ell
    -0.68
    lance
    -0.68
    lander
    -0.66
    gae
    -0.66
    hoff
    -0.64
    arthed
    -0.61
    den
    -0.61
    wine
    -0.58
    bid
    -0.57
    oub
    -0.57
    POSITIVE LOGITS
     necessary
    3.59
    necessary
    2.48
     needed
    2.26
     requisite
    2.24
    needed
    2.05
     required
    2.03
     appropriate
    1.73
     essential
    1.65
     feasible
    1.53
     warranted
    1.53
    Activations Density 0.015%

    No Known Activations