INDEX

Explanations

references to user-related operations, particularly in programming contexts

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

righted

-0.55

NameInMap

-0.55

 ویکی‌پدی

-0.55

errHandler

-0.54

 "..\..\..\

-0.51

 '\\;'

-0.50

 мәкал

-0.49

StructEnd

-0.49

 viewDidLoad

-0.48

DockStyle

-0.48

POSITIVE LOGITS

uclear

0.53

ゴリー

0.52

bibliography

0.52

वरण

0.51

where

0.50

Where

0.50

yntaxException

0.49

afone

0.49

 where

0.49

MessageState

0.48

Activations Density 0.073%

references to user-related operations, particularly in programming contexts

No Comments

No Known Activations