INDEX

Explanations

mentions of allies and associations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Funnel

-0.67

kasten

-0.64

AlterField

-0.63

setVerticalGroup

-0.60

 Manner

-0.59

กรม

-0.59

ValueStyle

-0.58

rometers

-0.58

 Interactions

-0.58

Orsay

-0.56

POSITIVE LOGITS

 allies

0.92

 Allies

0.89

 ally

0.72

 Rick

0.71

 allied

0.66

Rick

0.64

 coalition

0.62

ille

0.62

alition

0.61

vac

0.60

Activations Density 0.076%

mentions of allies and associations

No Comments

No Known Activations