INDEX

Explanations

phrases that express personal reflections and emotional experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 dommage

-0.40

 forder

-0.35

yyv

-0.34

 stano

-0.34

 pihaknya

-0.34

 Tenggara

-0.34

 Voyez

-0.33

 Store

-0.33

 diharapkan

-0.32

findall

-0.32

POSITIVE LOGITS

 myself

0.64

my

0.61

ValueStyle

0.52

 mijn

0.52

 okuyayım

0.49

myself

0.49

IContainer

0.47

ismet

0.46

 mojej

0.45

我的

0.44

Activations Density 0.935%

phrases that express personal reflections and emotional experiences

No Comments

No Known Activations