INDEX

Explanations

conversations and dialogue involving questions and responses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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



-0.58

脚注の使い方

-0.54

agoza

-0.51

izr

-0.50

fromnode

-0.49

RegressionTest

-0.49

 Annahme

-0.48

 onItemClick

-0.48

Activator

-0.47

IVEREF

-0.47

POSITIVE LOGITS

ask

1.36

Ask

1.26

Ask

1.25

 informing

1.20

 explain

1.18

 told

1.18

 tell

1.15

 explaining

1.14

 explained

1.13

 asked

1.12

Activations Density 0.396%

conversations and dialogue involving questions and responses

No Comments

No Known Activations