© 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. 2826
    Prev
    Next
    INDEX
    Explanations

    expressions of strong affection

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong affection and appreciation

    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
     Accounting
    -0.61
     Transcript
    -0.61
    izable
    -0.60
     hybrids
    -0.58
    Shape
    -0.57
     improvised
    -0.57
     plur
    -0.57
     randomized
    -0.57
    TRY
    -0.56
     Nanto
    -0.56
    POSITIVE LOGITS
     dearly
    1.27
     much
    1.11
     uncond
    1.08
     passionately
    1.05
     greatly
    1.01
    much
    1.00
     MUCH
    0.98
     badly
    0.91
     immensely
    0.88
     deeply
    0.87
    Activations Density 0.186%

    No Known Activations