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. 21008
    Prev
    Next
    INDEX
    Explanations

    mentions of the time period "decade."

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of a decade

    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
    ournals
    -0.81
     ingred
    -0.71
    iqu
    -0.69
    iquid
    -0.68
    anamo
    -0.67
     procedural
    -0.66
    perse
    -0.66
    hammad
    -0.66
    hemat
    -0.64
    room
    -0.64
    POSITIVE LOGITS
     ago
    0.94
     ILCS
    0.90
     Ago
    0.76
    uously
    0.75
    ĸļ
    0.72
     Anniversary
    0.72
    icity
    0.71
     onward
    0.70
    ary
    0.70
    èĪ
    0.68
    Activations Density 0.026%

    No Known Activations