INDEX

Explanations

numbers and relationships between keywords

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tidaknya

-0.50

warnings

-0.49

IARC

-0.48

 guerres

-0.47

 Grau

-0.47

stalline

-0.47

 MacGregor

-0.47

unread

-0.47

 chrétiens

-0.46

soni

-0.45

POSITIVE LOGITS

awtextra

0.87

 تضيفلها

0.73

 للمعارف

0.71

 bezeichneter

0.69

dafx

0.69

uxxxx

0.67



0.66

TagMode

0.64

GraphicsUnit

0.62

 متعلقه

0.61

Activations Density 0.311%

numbers and relationships between keywords

No Comments

No Known Activations