© 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. 1-RES-JB
    11. 9004
    Prev
    Next
    INDEX
    Explanations

    references to ransom situations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ransom or demands for payment in exchange for something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mood
    -0.74
     Hemp
    -0.73
     Einstein
    -0.73
    ________________
    -0.73
     Moment
    -0.73
     NCT
    -0.72
    Cola
    -0.70
     Anthrop
    -0.70
    Es
    -0.68
     Tid
    -0.68
    POSITIVE LOGITS
     ransom
    1.62
     extortion
    1.19
     challeng
    1.07
    ansom
    1.01
     attackers
    0.93
     kidn
    0.92
    peria
    0.88
     corrid
    0.81
     blackmail
    0.79
     payment
    0.79
    Activations Density 0.007%

    No Known Activations