INDEX

Explanations

terms related to insurance coverage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

WireFormatLite

-0.67

verifyException

-0.64

 ExecuteAsync

-0.58

parsedMessage

-0.57

ffffffff

-0.57

ècie

-0.55

Yess

-0.55

varargin

-0.52

/\.

-0.52

 Paglinawan

-0.51

POSITIVE LOGITS

 coverage

3.76

 Coverage

3.50

coverage

3.23

Coverage

3.21

 COVERAGE

2.95

 cobertura

1.88

 copertura

1.26

bertura

1.16

 couverture

1.15

 Covered

1.13

Activations Density 0.164%

terms related to insurance coverage

No Comments

No Known Activations