INDEX

Explanations

references to evidence and research findings

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

__':

-0.66

MeasureSpec

-0.62

 représ

-0.61

GraphicsUnit

-0.60

 destinées

-0.57

mobileqq

-0.56

Хро

-0.56

 pozn

-0.55

 appré

-0.55

ause

-0.53

POSITIVE LOGITS

 suggests

1.73

 suggest

1.64

 suggesting

1.51

sugges

1.44

suggest

1.37

 Sugges

1.37

 Suggest

1.33

 indicates

1.27

 sugiere

1.26

 SUGGEST

1.17

Activations Density 1.054%

references to evidence and research findings

No Comments

No Known Activations