INDEX

Explanations

mentions of "work" 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 @ 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

HtmlAttribute

-0.78

IntoConstraints

-0.67

Datuak

-0.63

NoSuchAlgorithm

-0.62

zzleHttp

-0.62

djangoproject

-0.62

pym

-0.58

RunWith

-0.57

gev

-0.57

Pautan

-0.57

POSITIVE LOGITS

 ethic

0.77

 work

0.66

horse

0.66

 done

0.65

Work

0.65

horses

0.64

 hard

0.63

 WORK

0.63

aday

0.61

 Work

0.61

Activations Density 0.129%

mentions of "work" in various contexts

No Comments

No Known Activations