INDEX

Explanations

concepts related to gaining something, whether it be knowledge, access, or an advantage

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

 Roberts

-0.66

 Stevenson

-0.64

 Schröder

-0.63

me

-0.62

 Peters

-0.60

 собой

-0.58

Me

-0.57

 precios

-0.57

POSITIVE LOGITS

 GAIN

1.62

 Gains

1.50

 Gain

1.48

gain

1.38

 gains

1.37

 gain

1.36

Gain

1.34

GAIN

1.28

 gained

1.27

gains

1.25

Activations Density 0.053%

concepts related to gaining something, whether it be knowledge, access, or an advantage

No Comments

No Known Activations