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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 21057
    Prev
    Next
    INDEX
    Explanations

    words related to specific concepts or themes such as poetry, emotions, science, and finance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to artistic expressions, emotions, and structural frameworks

    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
     nursing
    -0.76
    etheless
    -0.74
     fasting
    -0.66
    iles
    -0.62
     whipping
    -0.62
     quick
    -0.61
     whisk
    -0.61
     icing
    -0.61
     suburbs
    -0.61
     recorder
    -0.60
    POSITIVE LOGITS
    Gate
    0.98
     Opportun
    0.96
     Integrity
    0.91
     Accountability
    0.90
    Scene
    0.89
     Lobby
    0.89
     Coordinator
    0.88
     Guys
    0.88
     Wars
    0.88
     Direction
    0.87
    Activations Density 0.386%

    No Known Activations