INDEX

Explanations

references to programming constructs, particularly related to action handling and media types

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

-0.56

-0.54

-0.51

De

-0.50

-0.49

Re

-0.48

“

-0.48

-0.47

[]

-0.47

POSITIVE LOGITS

 متعلقه

0.98

 صوتيه

0.96

 Roskov

0.95

 Anſ

0.93

Билгалдахарш

0.93

 purpoſe

0.92

expandindo

0.91

 houſe

0.88

+#+#

0.87

 >=",

0.82

Activations Density 0.200%

references to programming constructs, particularly related to action handling and media types

No Comments

No Known Activations