INDEX

Explanations

phrases and contexts related to inquiry and evaluation

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

asking questions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

ViewImports

-0.45

GOTREF

-0.44

 quæ

-0.40

AddTagHelper

-0.38

ゴリー

-0.37

jsdelivr

-0.37

WriteTagHelper

-0.34

 uſed

-0.34

новниш

-0.34

crollView

-0.33

POSITIVE LOGITS

 unanswered

0.55

 anonymous

0.53

ronpa

0.49

 Anonymous

0.48

hallen

0.47

Zuh

0.47

jgl

0.46

 folks

0.46

הערות

0.46

KommentareTeilen

0.46

Activations Density 0.002%

phrases and contexts related to inquiry and evaluation

asking questions

No Comments

No Known Activations