INDEX

Explanations

phrases and terms related to measurement and evaluation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 Runde

-0.50

خاذ

-0.48

권

-0.44

 contextLoads

-0.43

ريد

-0.42

Medio

-0.41

classification

-0.41

Centa

-0.41

väg

-0.41

Clasificación

-0.40

POSITIVE LOGITS

 match

1.87

 matching

1.79

 coincide

1.76

 matches

1.70

 matched

1.69

 coincides

1.66

match

1.56

 coincid

1.52

 coincided

1.51

 correspond

1.50

Activations Density 1.140%

phrases and terms related to measurement and evaluation

No Comments

No Known Activations