INDEX

Explanations

mentions of unspecified people or individuals

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

Халык

-0.78

clusal

-0.67

 kasarigan

-0.66

 invokingState

-0.63

iNdEx

-0.61

TypedValue

-0.60

InvalidProtocol

-0.58

ñoz

-0.58

AndroidJUnit

-0.56

Raw

-0.56

POSITIVE LOGITS

 someone

1.32

someone

1.19

 somebody

1.17

 anyone

1.16

 anybody

1.09

anyone

1.08

Someone

1.01

 alguém

1.01

 SOMEONE

0.99

 iemand

0.97

Activations Density 0.184%

mentions of unspecified people or individuals

No Comments

No Known Activations