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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 8879
    Prev
    Next
    INDEX
    Explanations

    phrases related to themes of control, betrayal, revenge, and determination

    oai_token-act-pair · gpt-3.5-turbo

    themes of betrayal and vengeance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iosyncr
    -0.85
     anecd
    -0.81
    espie
    -0.71
     Cosponsors
    -0.71
     staffed
    -0.71
    audio
    -0.69
     CBO
    -0.69
    ricanes
    -0.69
    rowd
    -0.69
    FM
    -0.69
    POSITIVE LOGITS
    venge
    1.18
     immortality
    1.18
     revenge
    1.08
     eternity
    1.07
     aven
    1.04
     vengeance
    1.04
     betrayal
    1.03
     treacher
    1.01
     destiny
    1.00
     betray
    0.99
    Activations Density 1.069%

    No Known Activations