INDEX

Explanations

references to numeric ranges

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

^(@)

-1.26

 مشين

-1.26

脚注の使い方

-1.19

 CreateTagHelper

-1.19

 myſelf

-1.14

 للمعارف

-1.14

 itſelf

-1.11

UrlResolution

-1.11

 Infórmanos

-1.10

DockStyle

-1.07

POSITIVE LOGITS

 range

1.39

range

1.21

 Range

0.88

RANGE

0.85

 RANGE

0.84

Range

0.84

ange

0.84

 rango

0.83

 ranged

0.80

 rang

0.80

Activations Density 0.240%

references to numeric ranges

No Comments

No Known Activations