INDEX

Explanations

terms related to capacity or capability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 تانيه

-0.85

Ols

-0.81

]--;

-0.75

 nltk

-0.73

 Firestone

-0.72

cheat

-0.71

🏻

-0.69

 Fros

-0.69

 pygame

-0.69

Portail

-0.68

POSITIVE LOGITS

 capacity

1.86

 capacities

1.72

 Capacity

1.69

capacity

1.63

 CAPACITY

1.60

Capacity

1.50

 Capac

1.49

CAPACITY

1.49

 capac

1.27

Capac

1.24

Activations Density 0.060%

terms related to capacity or capability

No Comments

No Known Activations