INDEX

Explanations

phrases indicating a suggestion or recommendation

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

 Theſe

-0.66

 Anſ

-0.66

lapsingToolbar

-0.65

Efq

-0.65

 RSSSF

-0.62

المشاركات

-0.59

 Reſ

-0.58

 doubtnut

-0.56

IconModule

-0.56

Controllo

-0.56

POSITIVE LOGITS

 best

1.17

 wise

1.02

 smart

0.99

 advisable

0.99

 prudent

0.97

best

0.95

 smartest

0.89

smart

0.84

 wisest

0.82

 good

0.80

Activations Density 0.190%

phrases indicating a suggestion or recommendation

No Comments

No Known Activations