INDEX

Explanations

variations of the word "OK" indicating approval or acceptance

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

ok

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

TMS

-0.42

 experience

-0.42

firestore

-0.41

matrix

-0.40

 turi

-0.40

the

-0.39

ante

-0.39

ysty

-0.38

The

-0.37

 transform

-0.37

POSITIVE LOGITS

Ok

1.02

Ok

0.98

OK

0.97

ok

0.93

ok

0.88

OK

0.88

isOk

0.85

 Okada

0.81

addGap

0.73

OkHttpClient

0.71

Activations Density 0.007%

variations of the word "OK" indicating approval or acceptance

ok

No Comments

No Known Activations