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. 5-RES-JB
    6. 10604
    Prev
    Next
    INDEX
    Explanations

    words related to moral judgment and value

    oai_token-act-pair · gpt-3.5-turbo

    the concept of being 'worthy' or deserving of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cation
    -0.64
     Esk
    -0.64
     Rou
    -0.64
    esville
    -0.63
    ingo
    -0.62
    acid
    -0.62
    eteria
    -0.62
    zyme
    -0.62
    iq
    -0.61
    rief
    -0.60
    POSITIVE LOGITS
     worthy
    0.86
     deserving
    0.84
    lihood
    0.82
    minded
    0.81
     successors
    0.81
     successor
    0.79
     contenders
    0.76
    nesses
    0.76
     heirs
    0.75
     consideration
    0.73
    Activations Density 0.013%

    No Known Activations