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. 7859
    Prev
    Next
    INDEX
    Explanations

    dates or specific numerical sequences

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations or geographical areas

    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
    ificial
    -0.62
    angelo
    -0.62
    ulhu
    -0.60
    taboola
    -0.59
    nces
    -0.57
    zona
    -0.55
    ccording
    -0.54
    Cola
    -0.54
     ACTIONS
    -0.53
    arth
    -0.53
    POSITIVE LOGITS
    schild
    0.70
     Hutch
    0.59
    ansk
    0.57
     Esk
    0.57
    oice
    0.57
    pees
    0.57
    tein
    0.55
    iland
    0.55
    owship
    0.54
    ONSORED
    0.54
    Activations Density 1.218%

    No Known Activations