INDEX

Explanations

references to character perspectives and their backstories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 propOrder

-0.66

-0.60

ⓧ

-0.57

 localObject

-0.52

 ProtoMessage

-0.52

principalColumn

-0.51

 &___

-0.50

GOTREF

-0.48

writeFieldEnd

-0.47

ніципалі

-0.46

POSITIVE LOGITS

 '\\;'

0.42

+:+

0.39

-|-

0.36

这篇

0.34

Maw

0.34

 Hang

0.33

Individ

0.33

AW

0.33

oirs

0.33

zef

0.33

Activations Density 0.592%

references to character perspectives and their backstories

No Comments

No Known Activations