INDEX

Explanations

instances of the word "significant" and its variants, indicating a focus on notable outcomes or changes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

hand

-0.61

au

-0.53

on

-0.50

do

-0.49

-0.48

Top

-0.48

ো

-0.48

clothes

-0.47

ose

-0.47

ar

-0.47

POSITIVE LOGITS

 itſelf

1.04

ificant

1.04

 myſelf

1.01

 >=",

1.01

BibitemShut

0.95

')));

0.93

 ――――――――

0.92

DataAnnotations

0.91

)),

0.91

tagHelperRunner

0.91

Activations Density 0.273%

instances of the word "significant" and its variants, indicating a focus on notable outcomes or changes

No Comments

No Known Activations