INDEX

Explanations

terms related to vertical alignment or orientation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Gambas

-0.73

setTransform

-0.71

뀜

-0.68

 calendriers

-0.68

 ")");

-0.67

)<\

-0.67

odios

-0.66

AnchorTagHelper

-0.66

Personensuche

-0.66

---*/

-0.66

POSITIVE LOGITS

 vertical

2.13

 Vertical

2.04

Vertical

2.03

 horizontal

2.00

vertical

1.97

Horizontal

1.94

 Horizontal

1.90

 VERTICAL

1.86

 vertically

1.80

horizontal

1.76

Activations Density 0.082%

terms related to vertical alignment or orientation

No Comments

No Known Activations