INDEX

Explanations

instances of the word "know" in various contexts, highlighting uncertainty or self-awareness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

__":

-0.77

__':

-0.73

__':

-0.73

__":

-0.72

참고

-0.65

ografija

-0.64

 useCallback

-0.63

-0.58

Datuak

-0.58

Morfologia

-0.57

POSITIVE LOGITS

Busy

0.51

 Busy

0.51

 sabemos

0.51

 banget

0.50

 curtain

0.48

 Allot

0.47

我知道

0.46

 Garn

0.46

 busy

0.45

InvalidProtocol

0.44

Activations Density 0.173%

instances of the word "know" in various contexts, highlighting uncertainty or self-awareness

No Comments

No Known Activations