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. 5970
    Prev
    Next
    INDEX
    Explanations

    words related to a specific hallucinogenic substance

    oai_token-act-pair · gpt-3.5-turbo

    words associated with specific hallucinogenic substances

    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
     Freak
    -0.72
    gerald
    -0.65
     dearly
    -0.63
    llor
    -0.60
     hereafter
    -0.60
     <+
    -0.59
    FIX
    -0.59
    missions
    -0.59
     accidents
    -0.58
     glim
    -0.57
    POSITIVE LOGITS
    steen
    0.76
    ipedia
    0.74
    umen
    0.70
    quez
    0.70
    oso
    0.69
    iflower
    0.69
    phia
    0.69
    ucci
    0.67
    agne
    0.67
    hurst
    0.65
    Activations Density 0.311%

    No Known Activations