© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 15289
    Prev
    Next
    INDEX
    Explanations

    words related to jeopardizing or endangering something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to jeopardy or risk to safety and security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.86
    imb
    -0.65
    agn
    -0.62
    ann
    -0.62
    rikes
    -0.61
    gat
    -0.61
     likes
    -0.60
    row
    -0.59
    iterator
    -0.59
    Sher
    -0.59
    POSITIVE LOGITS
     jeopard
    1.20
     adolesc
    1.02
     endanger
    0.90
     undermin
    0.74
     compromising
    0.73
     Qiao
    0.72
     comprom
    0.67
    ashtra
    0.67
     certs
    0.67
     unnecess
    0.66
    Activations Density 0.016%

    No Known Activations