INDEX

Explanations

the word "name" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

ness

-0.60

-0.48

 matur

-0.46

ten

-0.46

nes

-0.45

ley

-0.45

our

-0.44

ly

-0.44

щихся

-0.43

NESS

-0.42

POSITIVE LOGITS

 name

2.32

 navnet

1.29

 names

1.27

 naam

1.19

 namanya

1.11

名前

1.05

ⓧ

1.05

 이름

1.03

rungsseite

1.03

名字

1.01

Activations Density 0.163%

the word "name" in various contexts

No Comments

No Known Activations