INDEX

Explanations

phrases indicating relationships or connections within a context

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

"in" or "of" followed by a noun

np_acts-logits-general · gemini-2.0-flash

describing nature or form

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

Personendaten

-0.74

 CreateTagHelper

-0.69

 متعلقه

-0.67

sizeCache

-0.63

 chi̍t

-0.58

AutoField

-0.56

 flexibility

-0.55

MemoryWarning

-0.55

oredCriteria

-0.55

XmlEnum

-0.54

POSITIVE LOGITS

 approach

0.76

approach

0.70

 nature

0.62

 dealings

0.61

approche

0.60

 handling

0.58

 approaches

0.58

 execution

0.56

 presentation

0.55

 offerings

0.55

Activations Density 0.459%

phrases indicating relationships or connections within a context

"in" or "of" followed by a noun

describing nature or form

No Comments

No Known Activations