INDEX

Explanations

references to comparisons or similarities

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

 houſe

-1.15

 raiſ

-1.10

 Houſe

-1.05

 Theſe

-1.03

 ſeveral

-1.01

 itſelf

-1.01

 myſelf

-1.01

 ſet

-1.00

 againſt

-0.98

 pleaſure

-0.96

POSITIVE LOGITS

ษัท

0.62

’

0.58

Co

0.57

cupertino

0.56

0.55

ไ

0.55

’

0.52

‍

0.51

•

0.50

ArgsConstructor

0.50

Activations Density 0.140%

references to comparisons or similarities

No Comments

No Known Activations