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. 5305
    Prev
    Next
    INDEX
    Explanations

    phrases related to family relationships

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating familial relationships

    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
    nels
    -0.83
    ngth
    -0.77
    aceous
    -0.76
    pport
    -0.74
    insk
    -0.73
    AE
    -0.73
    need
    -0.70
    force
    -0.70
    Downloadha
    -0.69
    tesy
    -0.68
    POSITIVE LOGITS
     immigrants
    0.81
     billionaire
    0.78
     slain
    0.76
     wealthy
    0.75
     Holocaust
    0.74
     Cul
    0.74
     immigrant
    0.73
     Emmy
    0.71
     Zeus
    0.71
     Martha
    0.71
    Activations Density 0.076%

    No Known Activations