INDEX

Explanations

quantitative data and numerical values represented in various formats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

いざ

-0.53

Array

-0.49

eably

-0.49

orsky

-0.48

目で

-0.45

-0.43

==

-0.43

skaya

-0.42

ero

-0.42

 Array

-0.41

POSITIVE LOGITS

تقاوى

0.95

+#+#

0.94

 betweenstory

0.85

 AssemblyCulture

0.84

mtrl

0.84

PerformLayout

0.82

UrlResolution

0.81

protoimpl

0.80

 myſelf

0.80

Jeografia

0.79

Activations Density 0.177%

quantitative data and numerical values represented in various formats

No Comments

No Known Activations