© 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. 4-RES-JB
    11. 22372
    Prev
    Next
    INDEX
    Explanations

    mentions related to risks and potential negative outcomes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to risk factors and risk-taking behavior

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

    No Comments

    Negative Logits
    abase
    -1.05
    ragon
    -0.90
    ADRA
    -0.89
    Football
    -0.77
    nice
    -0.76
    Nap
    -0.76
    Crystal
    -0.75
    çļ
    -0.70
    Michelle
    -0.69
     Blanc
    -0.69
    POSITIVE LOGITS
     harm
    0.87
     retribution
    0.84
     repercussions
    0.80
     harming
    0.80
     hazards
    0.78
     developing
    0.77
     pathogens
    0.77
     risks
    0.76
     litigation
    0.75
     pitfalls
    0.75
    Activations Density 0.180%

    No Known Activations