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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 900
    Prev
    Next
    INDEX
    Explanations

    instances where a passive form of the verb "to be" is followed by a high-frequency word

    oai_token-act-pair · gpt-3.5-turbo

    the past tense form of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Millions
    -0.65
     Individuals
    -0.62
     Mountains
    -0.62
     Hitch
    -0.61
    stood
    -0.61
     IMAGES
    -0.60
     Which
    -0.59
    Make
    -0.59
    know
    -0.58
     Extend
    -0.58
    POSITIVE LOGITS
    hes
    1.32
    nt
    1.01
    wolves
    0.99
    hers
    0.96
    wolf
    0.94
     supposed
    0.89
     originally
    0.88
     deemed
    0.88
     able
    0.85
     instrumental
    0.84
    Activations Density 0.401%

    No Known Activations