INDEX

Explanations

instances of names, titles, and terms related to subjects or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 myſelf

-0.83

 itſelf

-0.78

 Majefty

-0.76

 juſ

-0.76

 raiſ

-0.75

 Reſ

-0.74

 ſeveral

-0.73

 whoſe

-0.73

 poffible

-0.71

 ſche

-0.70

POSITIVE LOGITS

 simply

1.21

‘

1.07

1.00

simply

0.98

0.96

“

0.96

 simplesmente

0.92

 semplicemente

0.92

 appunto

0.91

 simplemente

0.90

Activations Density 0.228%

instances of names, titles, and terms related to subjects or concepts

No Comments

No Known Activations