INDEX

Explanations

various expressions of opinions and perceptions

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

 pomen

-0.54

xically

-0.46

رار

-0.43

 pří

-0.41

responsive

-0.40

רא

-0.39

configuration

-0.39

וקה

-0.39

 yapı

-0.39

ául

-0.39

POSITIVE LOGITS

 about

0.85

 propOrder

0.72

setVerticalGroup

0.71

JspWriter

0.70

 Formed

0.68

 formed

0.67

 betweenstory

0.66

expressed

0.64

GEBURTSDATUM

0.64

 expressed

0.63

Activations Density 0.460%

various expressions of opinions and perceptions

No Comments

No Known Activations