Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 22474
    Prev
    Next
    INDEX
    Explanations

    phrases related to theft and illegal activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of theft or stealing

    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
    ICAN
    -0.96
    natureconservancy
    -0.88
    FML
    -0.80
    HUD
    -0.75
    SPONSORED
    -0.73
    arella
    -0.71
    cular
    -0.70
    eele
    -0.70
    ICA
    -0.69
    QUI
    -0.68
    POSITIVE LOGITS
     contam
    0.75
     disguise
    0.72
     stolen
    0.66
     paradise
    0.66
     stash
    0.65
     carc
    0.64
     deposit
    0.64
    ishable
    0.63
     spoil
    0.63
     souven
    0.62
    Activations Density 0.399%

    No Known Activations