INDEX

Explanations

repetitions of the word "do"

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 ſta

-0.65

Efq

-0.61

 raiſ

-0.59

 Theſe

-0.58

 Conſ

-0.57

 againſt

-0.57

:✨

-0.57

 ſte

-0.56

 laſt

-0.56

 ſame

-0.55

POSITIVE LOGITS

do

1.14

 does

0.57

did

0.43

 FetchType

0.39

are

0.38

principalColumn

0.38

 šķ

0.36

da

0.34

 weder

0.34

idor

0.34

Activations Density 0.204%

repetitions of the word "do"

No Comments

No Known Activations