INDEX

Explanations

punctuation marks indicating pauses or changes in thought

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.35.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

 Whilst

-1.18

Whilst

-1.13

 whilst

-0.96

非常的

-0.91

 Anyways

-0.82

 however

-0.82

 אשר

-0.76

 skall

-0.76

 Firstly

-0.76

慢慢的

-0.75

POSITIVE LOGITS

onViewCreated

0.67

◗

0.63

AddTagHelper

0.63

 ligiloj

0.63

 queſta

0.62

ArrowToggle

0.60

 staffers

0.60

 SwitchCompat

0.60

こうした

0.58

expandindo

0.58

Activations Density 0.469%

punctuation marks indicating pauses or changes in thought

No Comments

No Known Activations