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. 4-RES-JB
    6. 5037
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives related to improvement or deterioration

    oai_token-act-pair · gpt-3.5-turbo

    references to improving and declining conditions

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

    No Comments

    Negative Logits
     entirety
    -0.68
    HO
    -0.65
     Bild
    -0.62
    chief
    -0.61
     originated
    -0.60
    never
    -0.59
    former
    -0.59
    Area
    -0.59
    ieu
    -0.59
     Hong
    -0.57
    POSITIVE LOGITS
    ãĤ¼
    0.90
     sidx
    0.79
     traction
    0.78
    noticed
    0.76
    retty
    0.75
     puberty
    0.73
     acquainted
    0.71
    ocobo
    0.71
     mileage
    0.71
     destro
    0.70
    Activations Density 0.085%

    No Known Activations