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. 10-RES-JB
    6. 1888
    Prev
    Next
    INDEX
    Explanations

    verbs in past or present tense depicting action or emotion

    oai_token-act-pair · gpt-3.5-turbo

    the verb "to be" in various tenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idth
    -0.75
     relates
    -0.72
     Lack
    -0.69
     coincides
    -0.68
    occ
    -0.65
    poke
    -0.65
     entails
    -0.65
     Contains
    -0.64
     derives
    -0.63
     weights
    -0.63
    POSITIVE LOGITS
     able
    1.19
     powerless
    1.16
     reunited
    1.11
     banished
    1.09
     rewarded
    1.08
     forced
    1.06
     hauled
    1.04
     reborn
    1.04
     unable
    1.03
     crowned
    1.03
    Activations Density 0.244%

    No Known Activations