© 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. 20875
    Prev
    Next
    INDEX
    Explanations

    words related to ransom situations or demands

    oai_token-act-pair · gpt-3.5-turbo

    references to ransom and ransom-related activities

    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
    Cola
    -0.85
    ________________
    -0.72
     Mood
    -0.72
     Anthrop
    -0.68
     Moment
    -0.66
     Einstein
    -0.64
    çĦ
    -0.62
    ergy
    -0.62
     Retro
    -0.62
    alist
    -0.60
    POSITIVE LOGITS
     ransom
    1.33
     extortion
    1.07
     kidn
    0.87
     attackers
    0.85
    ansom
    0.83
    ware
    0.79
    hyde
    0.78
    peria
    0.78
     challeng
    0.75
    ©¶æ¥µ
    0.75
    Activations Density 0.012%

    No Known Activations