© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 16313
    Prev
    Next
    INDEX
    Explanations

    information related to the tone and manner of speaking, focusing on aspects like calmness, politeness, and articulation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of emotional states or reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Liberties
    -0.84
    AAA
    -0.79
    çīĪ
    -0.79
     Spons
    -0.78
    ieves
    -0.77
     Funding
    -0.76
     GEAR
    -0.74
     NCT
    -0.74
    ormons
    -0.73
    igslist
    -0.72
    POSITIVE LOGITS
     calm
    1.31
     composure
    1.29
     sarcastic
    1.26
     condesc
    1.22
     demeanor
    1.21
     polite
    1.20
     witty
    1.14
     stern
    1.14
     understatement
    1.12
     dismissive
    1.12
    Activations Density 0.437%

    No Known Activations