INDEX

Explanations

negative signs or indicators

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

numbers followed by 1

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.32.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

AndEndTag

-0.66

MigrationBuilder

-0.62

KommentareTeilen

-0.60

Autoritní

-0.56

ніципалі

-0.55

 Autorizaciones

-0.53

 Signalez

-0.50

 OMITBAD

-0.49

 المعيارى

-0.49

 protoimpl

-0.48

POSITIVE LOGITS

 FetchType

0.45

 fometimes

0.42

merksamkeit

0.38

 itſelf

0.38

ulemon

0.37

 ſhould

0.37

 hormigón

0.36

 rembour

0.35

photographe

0.35

glement

0.35

Activations Density 0.024%

negative signs or indicators

numbers followed by 1

No Comments

No Known Activations