INDEX

Explanations

references to a specific medical condition or procedure

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

 recall

-0.75

 Recall

-0.72

 Normdatei

-0.70

 recalled

-0.66

ContentAsync

-0.66

CASH

-0.65

 ball

-0.64

 recalling

-0.64

recall

-0.63

OGND

-0.63

POSITIVE LOGITS

Ob

1.48

Ob

1.43

ob

1.30

ob

1.27

OB

1.13

OB

1.06

Obs

0.87

obs

0.73

obs

0.70

obie

0.66

Activations Density 0.055%

references to a specific medical condition or procedure

No Comments

No Known Activations