INDEX

Explanations

informative quantifiers and attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ItemLayout

-0.61

出版年

-0.60

say

-0.59

gup

-0.53

Say

-0.49

ider

-0.48

 însă

-0.48

Искәрмәләр

-0.48

say

-0.48

ltä

-0.47

POSITIVE LOGITS

EDEFAULT

0.63

tvguidetime

0.61

 للمعارف

0.57

mapStateToProps

0.57

 noDo

0.56

__.__

0.52

ResumeLayout

0.52

 tượng

0.50

 getRule

0.49

levard

0.49

Activations Density 0.028%

informative quantifiers and attributes

No Comments

No Known Activations