INDEX

Explanations

numerical figures, particularly statistics or data points

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 للمعارف

-0.83

webElementXpaths

-0.72

 <<<<<<<<<<<<<<

-0.71

CWE

-0.70

 IFTT

-0.66

liothèque

-0.66

 AttributeSet

-0.65

تقاوى

-0.62

 encomp

-0.61

InitVars

-0.61

POSITIVE LOGITS

↵↵

0.70

<eos>

0.61

FTFY

0.58

↵↵↵

0.55

↵↵↵↵

0.52

اريخ

0.50

HasColumnType

0.49

 suara

0.47

</blockquote>

0.47

conten

0.47

Activations Density 0.420%

numerical figures, particularly statistics or data points

No Comments

No Known Activations