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. 14319
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Ezra" with varying levels of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    references to specific artists or bands

    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
     Flavoring
    -0.74
     IGF
    -0.64
     Icelandic
    -0.64
    Else
    -0.62
     Yard
    -0.62
    NYSE
    -0.61
     NRL
    -0.59
     UID
    -0.59
     Sop
    -0.59
    ISTER
    -0.58
    POSITIVE LOGITS
    ombie
    0.95
    hner
    0.93
    edo
    0.92
    erate
    0.90
    illas
    0.90
    cellent
    0.89
    ing
    0.89
    hov
    0.84
    hao
    0.83
    gypt
    0.80
    Activations Density 0.027%

    No Known Activations