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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 7798
    Prev
    Next
    INDEX
    Explanations

    geographical and astronomical information

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to time, geography, and celestial bodies

    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
    PLA
    -0.80
    apons
    -0.78
    Sov
    -0.75
    Priv
    -0.74
     Flavoring
    -0.73
    GAN
    -0.72
     Marketable
    -0.70
    Lear
    -0.69
    sbm
    -0.68
    pkg
    -0.68
    POSITIVE LOGITS
     latitude
    0.93
     celestial
    0.86
    odiac
    0.85
     gravitational
    0.85
     eclips
    0.83
     coordinates
    0.81
     anomaly
    0.81
     GMT
    0.81
     orbiting
    0.81
     astronomical
    0.80
    Activations Density 0.234%

    No Known Activations