INDEX

Explanations

numerical values and symbols possibly related to data or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

########.

-0.77

الحياه

-0.77

makeConstraints

-0.72

 betweenstory

-0.68

andExpect

-0.67

AddTagHelper

-0.67

 postIndex

-0.66

principalColumn

-0.66

etheless

-0.65

 jsPsych

-0.64

POSITIVE LOGITS

MAXN

0.62

bürgermeister

0.56

 specially

0.52

 Settembre

0.51

uksessa

0.50

HQ

0.50

AutoresizingMask

0.50

UserID

0.49

 Ersten

0.49

-------------</

0.48

Activations Density 1.702%

numerical values and symbols possibly related to data or statistics

No Comments

No Known Activations