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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 18278
    Prev
    Next
    INDEX
    Explanations

    the word "Things" at various points in the text

    oai_token-act-pair · gpt-3.5-turbo

    the word "things" and its variations, indicating a focus on general situations or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iary
    -0.88
    bern
    -0.74
    iaries
    -0.74
     Flavoring
    -0.72
    âĢ¢âĢ¢
    -0.69
    ether
    -0.65
    asio
    -0.64
    lication
    -0.63
    Joined
    -0.63
    BILITY
    -0.63
    POSITIVE LOGITS
     happen
    1.02
     happened
    0.95
     transpired
    0.92
     escalated
    0.91
     escalate
    0.91
     happening
    0.88
     unfold
    0.87
     pertaining
    0.85
     unfolded
    0.83
     Happ
    0.80
    Activations Density 0.041%

    No Known Activations