INDEX

Explanations

numerical values and measurements

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

encre

-0.59

 Gerr

-0.58

Vou

-0.54

 Delia

-0.53

 InputDecoration

-0.52

jangkau

-0.51

}</

-0.51

 skú

-0.50

 Inland

-0.50

 dataSnapshot

-0.49

POSITIVE LOGITS

 виправивши

0.83

 MainAxisSize

0.78

½

0.74

 Half

0.73

حوالہ

0.69

½

0.69

 متعلقه

0.69

TargetException

0.68

Tembelea

0.68

️

0.67

Activations Density 0.129%

numerical values and measurements

No Comments

No Known Activations