INDEX

Explanations

references to possessive pronouns related to individuals

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

 ویکی‌پدیای

-0.61

 Мексичка

-0.59

IUrlHelper

-0.54

AddTagHelper

-0.53

########.

-0.53

出版年

-0.53

RTSC

-0.53

 ligiloj

-0.51

ScopeManager

-0.51

HasAnnotation

-0.49

POSITIVE LOGITS

own

0.73

 patients

0.68

 clients

0.67

 students

0.65

 employees

0.61

 colleagues

0.61

 countrymen

0.59

 organisation

0.59

 staff

0.59

 colleague

0.59

Activations Density 0.366%

references to possessive pronouns related to individuals

No Comments

No Known Activations