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. 6-RES-JB
    6. 16270
    Prev
    Next
    INDEX
    Explanations

    phrases related to manipulation or deception

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating manipulation or coercion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     summarizes
    -0.65
    clips
    -0.65
     traced
    -0.64
    anwhile
    -0.63
    fleet
    -0.63
     remarked
    -0.63
    lang
    -0.63
    Internet
    -0.63
    thora
    -0.63
     Rosenstein
    -0.63
    POSITIVE LOGITS
     surrender
    0.87
     submission
    0.85
     obedience
    0.83
     acquies
    0.72
     embrace
    0.72
     heel
    0.71
     favour
    0.71
     believing
    0.70
     staying
    0.70
     cooperate
    0.69
    Activations Density 0.152%

    No Known Activations