INDEX

Explanations

phrases related to abilities and capabilities

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

 MainAxisSize

-0.85

 insuffisamment

-0.69

红的

-0.64

 Fros

-0.60

 Chiu

-0.60

quar

-0.59

خر

-0.59

ge

-0.57

 سرخ

-0.57

 parseFrom

-0.57

POSITIVE LOGITS

 ability

2.97

 Ability

2.71

 abilities

2.55

Ability

2.53

 Abilities

2.13

ability

1.97

 capability

1.94

Abilities

1.75

abilities

1.72

 capabilities

1.72

Activations Density 0.056%

phrases related to abilities and capabilities

No Comments

No Known Activations

phrases related to abilities and capabilities

No Comments

No Known Activations