INDEX

Explanations

references to figures and visual data representations 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 @ 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

 виправивши

-0.68

躇

-0.65

printLine

-0.64

-------

-0.64

Kanpo

-0.63

 Portail

-0.62

 vPvB

-0.62

enumi

-0.62

 dealloc

-0.60

 SqlCommand

-0.59

POSITIVE LOGITS

ValueStyle

0.58

PageRoute

0.57

发表于

0.55

TabStop

0.52

 Wayback

0.51

BASEPATH

0.51

&=&\

0.51

voz

0.50

RectangleBorder

0.48

Figures

0.48

Activations Density 0.096%

references to figures and visual data representations in the text

No Comments

No Known Activations