Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 12609
    Prev
    Next
    INDEX
    Explanations

    words related to coercion and blackmail

    oai_token-act-pair · gpt-3.5-turbo

    terms related to coercion and manipulation

    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
    riot
    -0.76
    gal
    -0.76
    ikes
    -0.75
     Purpose
    -0.74
    den
    -0.74
    ARK
    -0.73
     Blessed
    -0.72
     Maintenance
    -0.72
    day
    -0.71
    ark
    -0.70
    POSITIVE LOGITS
     coer
    1.33
     coerced
    1.31
     coercion
    1.14
     coerc
    1.04
     pressured
    0.95
     coercive
    0.92
     blackmail
    0.90
     pressuring
    0.87
     compel
    0.85
     tricked
    0.85
    Activations Density 0.016%

    No Known Activations