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. 7651
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the availability of files or resources for download

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to downloading and software updates

    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
    xual
    -0.74
    heastern
    -0.73
    avering
    -0.68
    uncture
    -0.67
    ukemia
    -0.66
    ieu
    -0.65
    Dutch
    -0.64
    otics
    -0.63
    weak
    -0.63
    pher
    -0.63
    POSITIVE LOGITS
    DragonMagazine
    0.93
     downloaded
    0.87
     files
    0.81
     FREE
    0.78
    20439
    0.77
     ZIP
    0.77
     file
    0.77
     archive
    0.77
     ILCS
    0.75
     spreadsheet
    0.74
    Activations Density 0.161%

    No Known Activations