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. 5663
    Prev
    Next
    INDEX
    Explanations

    statements or quotes from various individuals

    oai_token-act-pair · gpt-3.5-turbo

    statements or direct quotations from individuals

    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
    Newsletter
    -0.90
    200000
    -0.72
    caliber
    -0.70
    BUG
    -0.70
    Exit
    -0.70
    physical
    -0.69
    soDeliveryDate
    -0.69
    ILA
    -0.68
    PHOTOS
    -0.68
     favor
    -0.68
    POSITIVE LOGITS
     afterwards
    1.00
     organisers
    0.92
     apologise
    0.91
     apologised
    0.90
     analyse
    0.89
     analys
    0.89
     recogn
    0.83
     organising
    0.83
     whilst
    0.82
     recognise
    0.82
    Activations Density 0.156%

    No Known Activations