INDEX

Explanations

terms related to small or miniature objects and their characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

yafet

-0.58

vės

-0.56

 terbesar

-0.54

cosh

-0.50

OLIC

-0.46

 umum

-0.45

lyst

-0.45

rekte

-0.44

[:,

-0.44

rials

-0.43

POSITIVE LOGITS

 small

1.28

 tiny

1.27

Small

1.23

 smaller

1.21

 SMALL

1.20

small

1.19

 Smaller

1.19

 Small

1.19

Smaller

1.15

Tiny

1.09

Activations Density 1.052%

terms related to small or miniature objects and their characteristics

No Comments

No Known Activations