INDEX

Explanations

references to blood and related terms

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

 CreateTagHelper

-0.88

 تضيفلها

-0.88

enumi

-0.78

Népesség

-0.70

 OMITBAD

-0.69

writeField

-0.68

AutoresizingMask

-0.67

 BoxFit

-0.67

andidaten

-0.66

providedIn

-0.66

POSITIVE LOGITS

 pressure

0.64

thirsty

0.63

 sugar

0.63

 plasma

0.62

sue

0.60

sugar

0.59

 transfusion

0.59

 vessel

0.58

 blood

0.57

Activations Density 0.118%

references to blood and related terms

No Comments

No Known Activations