INDEX

Explanations

expressions seeking clarification or explanation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 resourceCulture

-0.84

InjectAttribute

-0.81

CloseOperation

-0.72

GEBURTSDATUM

-0.70

UIControlState

-0.69

RetentionPolicy

-0.68

RenderAtEndOf

-0.67

 MainAxisSize

-0.66

jspb

-0.65

POSITIVE LOGITS

 explanation

0.95

 clarify

0.90

 explained

0.85

 explain

0.85

 clarifies

0.84

 explanations

0.82

 clarified

0.81

 clarification

0.80

explanation

0.75

 EXPLANATION

0.75

Activations Density 0.401%

expressions seeking clarification or explanation

No Comments

No Known Activations