INDEX

Explanations

terms associated with repetition, reevaluation, or reprocessing in various contexts

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

psack

-0.60

providedIn

-0.59

wpi

-0.55

jspx

-0.53

Odkazy

-0.51

 valueForKey

-0.50

Grpc

-0.50

 base

-0.49

 habido

-0.48

beeren

-0.47

POSITIVE LOGITS

 reissue

1.39

 reread

1.18

 rerun

1.17

 readjust

1.13

 reconsideration

1.13

 retraining

1.11

 redesign

1.10

 rejoined

1.09

 reactiv

1.09

 rewatch

1.09

Activations Density 0.280%

terms associated with repetition, reevaluation, or reprocessing in various contexts

No Comments

No Known Activations