INDEX

Explanations

instances of claims and references to legal allegations or complaints

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

OGND

-0.90

randomUUID

-0.88

 فريبيس

-0.88

 AssemblyCulture

-0.85

SequentialGroup

-0.84

 EdgeInsets

-0.83

XmlSchema

-0.78

각주

-0.77

脚注の使い方

-0.77

angdong

-0.77

POSITIVE LOGITS

 claims

1.16

 Claims

1.16

 claim

1.06

Claims

1.03

claims

1.03

 Claim

1.02

 CLAIMS

0.95

Claim

0.89

claim

0.89

 CLAIM

0.87

Activations Density 0.129%

instances of claims and references to legal allegations or complaints

No Comments

No Known Activations