INDEX

Explanations

concepts and descriptions of comfort and comfortability

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PathVariable

-0.80

ArrowToggle

-0.76

########.

-0.75

CodeAttribute

-0.74

bootstrapcdn

-0.73

 Bateman

-0.68

plyr

-0.67

MDB

-0.67

 Keyes

-0.66

 locust

-0.66

POSITIVE LOGITS

 comfort

2.25

 comfortable

2.19

Comfort

2.15

 Comfort

2.14

 COMFORT

2.11

comfort

2.05

Comfortable

1.97

 Comfortable

1.97

comfortable

1.90

 comfor

1.85

Activations Density 0.038%

concepts and descriptions of comfort and comfortability

No Comments

No Known Activations