INDEX

Explanations

terms related to verification and consistency checking in scientific data

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

 CreateTagHelper

-0.74

MLLoader

-0.64

Jeografia

-0.59

TypedDataSet

-0.57

án

-0.56

DockStyle

-0.54

 Portail

-0.53

Portail

-0.52

 kiệm

-0.50

OGND

-0.50

POSITIVE LOGITS

 check

2.52

 checking

2.42

 checks

2.33

check

2.30

 checked

2.25

 Check

2.21

 Checking

2.15

 CHECK

2.13

Check

2.11

 verify

2.08

Activations Density 0.736%

terms related to verification and consistency checking in scientific data

No Comments

No Known Activations