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. 5397
    Prev
    Next
    INDEX
    Explanations

    employment-related terms and activities, such as hiring, recruitment, and employment impacts

    oai_token-act-pair · gpt-3.5-turbo

    references to groups or categories of individuals

    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
    cknow
    -0.82
    SourceFile
    -0.69
     Press
    -0.66
    ModLoader
    -0.64
     prosecutor
    -0.61
    OLOG
    -0.61
    £
    -0.60
    orse
    -0.59
     Manufacturer
    -0.59
     Caption
    -0.59
    POSITIVE LOGITS
    hip
    1.29
    hips
    1.20
     arriving
    0.94
     fleeing
    0.91
     migrating
    0.90
    pace
    0.86
    needed
    0.86
    ourced
    0.85
    untled
    0.84
    ylum
    0.82
    Activations Density 0.375%

    No Known Activations