INDEX

Explanations

reported statements or claims made by individuals

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

 صوتيه

-0.72

NameInMap

-0.71

tagext

-0.68

icium

-0.56

 kaarangay

-0.54

duff

-0.53

DllImport

-0.52

oa̍t

-0.51

Ikus

-0.49

omoto

-0.49

POSITIVE LOGITS

 himſelf

0.81

 himself

0.69

 发表于

0.67

BagLayout

0.66

himself

0.64

 ſhe

0.62

Efq

0.60

 chofe

0.59

tagHelper

0.59

 ↓,

0.58

Activations Density 0.944%

reported statements or claims made by individuals

No Comments

No Known Activations