INDEX

Explanations

references to the concept of "capacity" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

uniforms

-0.68

Ols

-0.66

 Fros

-0.66

 تانيه

-0.64

cheat

-0.64

 haired

-0.64

 strs

-0.63

 firent

-0.61

 htons

-0.61

 wezen

-0.61

POSITIVE LOGITS

 capacity

3.59

 Capacity

3.20

capacity

3.13

 capacities

2.97

 CAPACITY

2.97

Capacity

2.95

CAPACITY

2.60

 Capac

2.13

 capacidad

2.12

 capac

2.04

Activations Density 0.039%

references to the concept of "capacity" in various contexts

No Comments

No Known Activations