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. 908
    Prev
    Next
    INDEX
    Explanations

    keywords related to software updates and events

    oai_token-act-pair · gpt-3.5-turbo

    references to updates or changes in technology

    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
    ï¸ı
    -0.60
    á½
    -0.57
     Byte
    -0.57
     thor
    -0.56
    ãĥ³ãĤ¸
    -0.54
    Balt
    -0.54
     mism
    -0.53
    actionDate
    -0.53
     GOODMAN
    -0.53
    cffffcc
    -0.52
    POSITIVE LOGITS
    heit
    0.90
    llah
    0.74
    iversary
    0.65
    ahime
    0.56
     Spirits
    0.56
     Tanzania
    0.54
    yles
    0.54
     reign
    0.54
     prayers
    0.54
    araoh
    0.53
    Activations Density 1.238%

    No Known Activations