INDEX

Explanations

various forms of the word "criteria."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

Ca

-0.72

Ca

-0.69

Rosario

-0.59

-0.58

 Benny

-0.56

 being

-0.49

зд

-0.49

matical

-0.48

 Silber

-0.48

strecke

-0.48

POSITIVE LOGITS

 Criteria

1.13

Criteria

1.09

 CRITERIA

1.00

criteria

0.92

NewUrlParser

0.91

 useState

0.90

 criteria

0.87

érêt

0.86

 useCallback

0.84

Datuak

0.82

Activations Density 0.034%

various forms of the word "criteria."

No Comments

No Known Activations