INDEX

Explanations

terms related to significant quantities or measures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

хьтан

-0.62

mif

-0.59

copyOf

-0.59

 eterno

-0.57

 tarko

-0.57

mphony

-0.56

плек

-0.55

;#

-0.55

ضب

-0.54

 empêche

-0.53

POSITIVE LOGITS

considerable

1.19

 considerable

1.18

 quite

1.09

 sizeable

1.07

 непло

1.07

 sizable

1.05

quite

1.04

 Considerable

1.01

 substantial

0.99

 bastante

0.97

Activations Density 0.345%

terms related to significant quantities or measures

No Comments

No Known Activations