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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 21559
    Prev
    Next
    INDEX
    Explanations

    passive voice constructions indicating an action that has already taken place

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "had been" in various contexts

    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
    ively
    -0.70
    rones
    -0.70
    ives
    -0.67
    iveness
    -0.62
    rates
    -0.60
    essee
    -0.60
    anth
    -0.60
    ($
    -0.60
    arta
    -0.60
    erity
    -0.60
    POSITIVE LOGITS
     able
    0.97
    wolves
    0.93
    cffffcc
    0.93
     subjected
    0.92
     beaten
    0.89
     mistaken
    0.87
     notified
    0.85
     replaced
    0.84
     blown
    0.84
     treated
    0.83
    Activations Density 0.103%

    No Known Activations