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. 21407
    Prev
    Next
    INDEX
    Explanations

    phrases related to the pharmaceutical company Merck

    oai_token-act-pair · gpt-3.5-turbo

    references to the company Merck

    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
     IMAGES
    -0.73
    »Ĵ
    -0.68
     Piercing
    -0.68
     Âł Âł Âł Âł Âł Âł Âł Âł
    -0.67
     microwave
    -0.65
     Eleven
    -0.62
    ¬¼
    -0.62
     Siege
    -0.60
     Defendants
    -0.60
     microw
    -0.60
    POSITIVE LOGITS
    cedes
    1.16
    seys
    1.12
    lins
    1.06
    itism
    1.02
    gers
    1.02
    ged
    1.01
    ger
    1.00
    ril
    0.99
    maid
    0.96
    ging
    0.95
    Activations Density 0.008%

    No Known Activations