INDEX

Explanations

the word "mere" in various contexts

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

simple or small quantities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

IntoConstraints

-0.69

transQ

-0.66

anskje

-0.63

 electrolux

-0.63

 anſ

-0.62

 Anſ

-0.61

 faſt

-0.59

 themſelves

-0.58

 itſelf

-0.58

ſelves

-0.58

POSITIVE LOGITS

 mere

1.97

mere

1.59

Mere

1.51

 Mere

1.47

 merely

1.15

 mera

0.85

 sheer

0.83

 simply

0.73

 مجرد

0.71

 meras

0.70

Activations Density 0.003%

the word "mere" in various contexts

simple or small quantities

No Comments

No Known Activations