INDEX

Explanations

references to "individual" and related terms indicating singular entities or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 amnesty

-0.72

wps

-0.67

Fon

-0.65

hynch

-0.64

ámara

-0.60

urns

-0.60

 bailout

-0.58

 Koning

-0.58

Bains

-0.58

 scare

-0.58

POSITIVE LOGITS

ividual

1.45

 individual

1.22

 INDIVIDUAL

1.21

 Individual

1.20

idual

1.18

Individuals

1.16

IVIDUAL

1.15

Individual

1.14

 individuals

1.12

 Individuals

1.09

Activations Density 0.040%

references to "individual" and related terms indicating singular entities or measurements

No Comments

No Known Activations