© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 17563
    Prev
    Next
    INDEX
    Explanations

    terms or phrases related to cosmic concepts and phenomena

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cosmic phenomena and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iage
    -1.23
    lund
    -0.97
    abet
    -0.92
    onet
    -0.92
    stood
    -0.90
    skirts
    -0.90
    topic
    -0.87
    yk
    -0.85
    iability
    -0.84
    yrim
    -0.83
    POSITIVE LOGITS
     rays
    1.33
     ray
    1.02
     cosmic
    0.80
     radiation
    0.79
     microwave
    0.79
     proportions
    0.77
     anomalies
    0.75
     Cosmic
    0.73
     energies
    0.69
     gloom
    0.69
    Activations Density 0.040%

    No Known Activations