INDEX

Explanations

expressions of fascination or intrigue related to various topics

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

декват

-0.54

 match

-0.52

piecz

-0.52

大利

-0.52

 aéreo

-0.52

AccessorTable

-0.51

Whoops

-0.51

üksek

-0.51

 Match

-0.51

 Tsche

-0.51

POSITIVE LOGITS

 fascination

1.70

 fascinated

1.65

 fascinating

1.64

 fascin

1.45

 curiosity

1.14

cinating

1.12

 intrigued

1.10

 faszin

1.10

Fas

0.98

 intriguing

0.97

Activations Density 0.137%

expressions of fascination or intrigue related to various topics

No Comments

No Known Activations