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. 2368
    Prev
    Next
    INDEX
    Explanations

    occurrences of the preposition "in" within a sentence

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "in" and its variations in different 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
    CLASSIFIED
    -0.72
     lodged
    -0.65
     %%
    -0.65
    username
    -0.65
    casters
    -0.62
    bryce
    -0.62
    $$
    -0.61
    HAEL
    -0.61
    catentry
    -0.61
    hur
    -0.59
    POSITIVE LOGITS
     conjunction
    1.29
     accordance
    1.29
     lieu
    1.26
     vain
    1.26
     unison
    1.21
     vitro
    1.20
    clusively
    1.17
     tandem
    1.14
     situ
    1.13
    ordinate
    1.10
    Activations Density 0.430%

    No Known Activations