© 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. 0-RES-JB
    11. 19883
    Prev
    Next
    INDEX
    Explanations

    phrases related to setting the tone or ambiance

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "tone" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    irl
    -0.69
    WAR
    -0.66
    vest
    -0.65
    served
    -0.65
    associated
    -0.65
    arent
    -0.64
    arians
    -0.63
     Feder
    -0.63
     Inv
    -0.63
     Fulton
    -0.62
    POSITIVE LOGITS
     tone
    3.92
     tones
    2.65
    tone
    2.61
     Tone
    2.44
    tones
    1.51
     complexion
    1.48
     mood
    1.41
     demeanor
    1.36
     vibe
    1.30
     temperament
    1.26
    Activations Density 0.020%

    No Known Activations