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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 21434
    Prev
    Next
    INDEX
    Explanations

    news articles or headlines related to law enforcement and legal incidents

    oai_token-act-pair · gpt-3.5-turbo

    reports of incidents involving law enforcement and political activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ModLoader
    -0.66
    mittedly
    -0.65
    intend
    -0.64
    ÙĴ
    -0.63
    omever
    -0.62
    theless
    -0.62
     Adin
    -0.60
    oaded
    -0.59
    76561
    -0.58
    approximately
    -0.58
    POSITIVE LOGITS
     Replay
    1.08
     |
    0.88
    ↵
    0.84
     Copyright
    0.83
     pic
    0.82
     Belfast
    0.81
     Shutterstock
    0.76
     copied
    0.75
     Read
    0.72
     »
    0.72
    Activations Density 2.242%

    No Known Activations