INDEX

Explanations

expressions of confusion or uncertainty

oai_token-act-pair · gpt-4o-mini Triggered by @bot

"even" and its negative connotations

np_acts-logits-general · gemini-2.0-flash

even

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ſtate

-0.70

AddHtmlAttribute

-0.69

 Chriſt

-0.64

 alſo

-0.64

 Jefus

-0.62

 purpoſe

-0.62

 ſtill

-0.61

TagMode

-0.60

/**

-0.60

 ſeveral

-0.59

POSITIVE LOGITS

 siquiera

0.81

 remotely

0.76

 bother

0.74

 bothering

0.72

binaan

0.67

 half

0.65

 bothered

0.64

 even

0.64

 barely

0.57

影子

0.54

Activations Density 0.081%

expressions of confusion or uncertainty

"even" and its negative connotations

even

No Comments

No Known Activations