INDEX

Explanations

terms indicating uncertainty or questioning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

sieger

-0.54

endregion

-0.52

 gradova

-0.51

bu

-0.50

といけない

-0.47

moveToNext

-0.46

uxxxx

-0.46

عادة

-0.46

 fall

-0.45

expandindo

-0.45

POSITIVE LOGITS

 doubtful

0.91

 questionable

0.89

 questioning

0.88

 dubious

0.82

 whether

0.81

 doubting

0.80

 cuestion

0.75

whether

0.72

Doubt

0.72

 doubted

0.71

Activations Density 0.347%

terms indicating uncertainty or questioning

No Comments

No Known Activations