INDEX

Explanations

references to people and their roles or titles within a professional context

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

<?

-0.71

principalColumn

-0.55

+#+#

-0.53

]--;

-0.51

 lượng

-0.50

getchar

-0.50

 getchar

-0.49

shire

-0.49

GEBURTSDATUM

-0.48

 CGFloat

-0.47

POSITIVE LOGITS

 للمعارف

0.69

 protoimpl

0.67

ffindor

0.58

 extiende

0.58

ftagPool

0.56

MessageTagHelper

0.54

 celulares

0.54

 leggi

0.54

 féminine

0.54

 peine

0.53

Activations Density 0.097%

references to people and their roles or titles within a professional context

No Comments

No Known Activations