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

    Neuronpedia

    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. 10-RES-JB
    11. 16985
    Prev
    Next
    INDEX
    Explanations

    terms related to resonance and connection

    oai_token-act-pair · gpt-3.5-turbo

    words related to emotional impact and connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lawy
    -0.75
    ©¶æ
    -0.73
    oops
    -0.71
    ãĥīãĥ©
    -0.67
    cheat
    -0.63
    nsics
    -0.62
    legal
    -0.62
    ctic
    -0.61
    onnaissance
    -0.60
    upper
    -0.60
    POSITIVE LOGITS
     resonate
    1.19
     reson
    1.18
     powerfully
    1.06
     resonance
    1.02
     deeply
    0.99
     strongly
    0.95
     louder
    0.91
     reverber
    0.88
     sentiments
    0.84
     loudly
    0.81
    Activations Density 0.085%

    No Known Activations