INDEX

Explanations

actions and prompts related to starting or initiating activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

MigrationBuilder

-1.19

LookAnd

-1.10

 Савезне

-0.88

 كومونز

-0.88

 الرياضيه

-0.87

BeginContext

-0.86

 estimés

-0.86

Билгалдахарш

-0.84

 esternos

-0.81

@"/

-0.78

POSITIVE LOGITS

 work

0.76

 busy

0.66

 WORK

0.59

work

0.58

 immediately

0.58

 business

0.57

 Work

0.57

 straight

0.55

Work

0.54

busy

0.53

Activations Density 0.143%

actions and prompts related to starting or initiating activities

No Comments

No Known Activations