INDEX

Explanations

repeated mentions of certain significant terms, particularly related to specific entities or topics in a context such as legal or scientific discussions

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

OOTDTY

-0.78

GOTREF

-0.77

 AssemblyTitle

-0.71

 StringTokenizer

-0.71

Rüyada

-0.68

Jeografia

-0.66

 initComponents

-0.65

ThemeOverlay

-0.65

 initView

-0.65

awtextra

-0.64

POSITIVE LOGITS

لاثة

0.64

ker

0.58

obald

0.57

 societies

0.56

Pla

0.55

createStatement

0.55

Mode

0.54

FILES

0.54

Pla

0.54

 Public

0.54

Activations Density 0.100%

repeated mentions of certain significant terms, particularly related to specific entities or topics in a context such as legal or scientific discussions

No Comments

No Known Activations