INDEX

Explanations

references to flat surfaces or items described as flat

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

Personendaten

-1.00

ChildScrollView

-0.69

 llorar

-0.69

 Nước

-0.69

Efq

-0.68

存于互联网档案馆

-0.67

simpleType

-0.66

 therefor

-0.65

TagMode

-0.65

Filmographie

-0.65

POSITIVE LOGITS

 flat

1.12

flat

1.04

Flat

0.94

 Flat

0.89

 neutral

0.81

vs

0.74

 FLAT

0.72

Neutral

0.70

FLAT

0.67

 flattened

0.65

Activations Density 0.076%

references to flat surfaces or items described as flat

No Comments

No Known Activations