INDEX

Explanations

visual elements and references to images or figures in the text

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

########.

-0.77

 EconPapers

-0.67

 فريبيس

-0.60

发表于

-0.58

Portail

-0.54

gameserver

-0.52

Portale

-0.51

IUrlHelper

-0.51

XmlAccessType

-0.50

addCriterion

-0.48

POSITIVE LOGITS

 below

1.06

 above

0.81

bove

0.74

below

0.71

 nedan

0.67

 bellow

0.66

 BELOW

0.66

 Below

0.65

 powy

0.64

 abaixo

0.63

Activations Density 0.459%

visual elements and references to images or figures in the text

No Comments

No Known Activations