INDEX

Explanations

technical terms and code-related elements, particularly those associated with programming and software design

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

ysty

-0.62

IsContent

-0.57

Rhestr

-0.55

balleur

-0.55

CppMethod

-0.54

umir

-0.53

پیوند

-0.53

 meines

-0.52

';

-0.52

Olvid

-0.51

POSITIVE LOGITS

 Brust

0.69

 impea

0.68

 Sanderson

0.67

 Winfrey

0.61

หวัด

0.60

infinity

0.60

 Gaylord

0.60

 chest

0.58

 CreateTagHelper

0.57

 impeachment

0.57

Activations Density 3.014%

technical terms and code-related elements, particularly those associated with programming and software design

No Comments

No Known Activations