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. 23795
    Prev
    Next
    INDEX
    Explanations

    prepositions in phrases depicting different types of actions or situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "turn to" indicating reliance or seeking assistance

    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
     conveyed
    -0.73
     levied
    -0.68
     bombed
    -0.67
     stoked
    -0.66
     caused
    -0.64
    bur
    -0.64
    intosh
    -0.64
     differed
    -0.63
     transmitted
    -0.63
     disagreed
    -0.63
    POSITIVE LOGITS
    ggles
    0.87
    othy
    0.78
    odan
    0.75
     repentance
    0.73
    WARD
    0.71
    ãĤ¨ãĥ«
    0.70
    pload
    0.70
     sidx
    0.69
     conserve
    0.69
     incorporate
    0.68
    Activations Density 0.068%

    No Known Activations