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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    11. 17433
    Prev
    Next
    INDEX
    Explanations

    words related to risks or dangers

    oai_token-act-pair · gpt-3.5-turbo

    references to perceived dangers or risks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    puted
    -0.81
    mys
    -0.78
    raham
    -0.74
    bits
    -0.74
    ilts
    -0.71
    arist
    -0.71
    ria
    -0.69
    gans
    -0.68
    unes
    -0.68
    ANN
    -0.67
    POSITIVE LOGITS
     threat
    1.13
     threats
    0.98
     Threat
    0.93
     proble
    0.92
    threat
    0.89
     posed
    0.86
     deterrent
    0.85
     menace
    0.84
     challeng
    0.84
     undermin
    0.83
    Activations Density 0.017%

    No Known Activations