INDEX

Explanations

mentions of "processing" in various contexts

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

processing operations and contexts

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

 AttributeSet

-0.52

Portail

-0.41

DateRange

-0.40

setDuration

-0.39

lessly

-0.38

FIGURE

-0.38

 UIFont

-0.38

Enllaços

-0.38

ophanes

-0.38

AttributeSet

-0.38

POSITIVE LOGITS

 Processing

0.85

 processing

0.83

 PROCESSING

0.81

Processing

0.80

processing

0.76

PROCESSING

0.65

 Verarbeitung

0.62

iented

0.60

 procesamiento

0.59

 processors

0.56

Activations Density 0.018%

mentions of "processing" in various contexts

processing operations and contexts

No Comments

No Known Activations