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. 9901
    Prev
    Next
    INDEX
    Explanations

    words related to legal terms, specifically those related to assisted suicide laws

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "su" and its variations, indicating a focus on topics related to suicide

    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
     Gutenberg
    -0.77
    neck
    -0.69
    Micro
    -0.60
     Turks
    -0.59
     louder
    -0.58
     Schwe
    -0.58
    bug
    -0.58
    head
    -0.57
     anx
    -0.56
     pain
    -0.56
    POSITIVE LOGITS
    icide
    1.33
    arez
    1.18
    zanne
    1.12
    pper
    1.08
    perty
    1.08
    icides
    1.07
    perm
    1.07
    selage
    1.01
    icidal
    0.99
    ggle
    0.92
    Activations Density 0.025%

    No Known Activations