INDEX

Explanations

phrases suggesting user engagement or conversational prompts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

 comment

-0.50

 writer

-0.50

iredo

-0.50

 Comment

-0.49

timewa

-0.49

 anon

-0.49

.“

-0.48

 Anon

-0.48

“...

-0.47

="@

-0.47

POSITIVE LOGITS

 виправивши

0.74

________________

0.72

OGND

0.71

Attached

0.68

 Normdatei

0.63

 Gonna

0.59

 Gotta

0.59

Enviado

0.58

 defStyleAttr

0.58

Добавлено

0.57

Activations Density 0.074%

phrases suggesting user engagement or conversational prompts

No Comments

No Known Activations