INDEX

Explanations

phrases related to questions, lists, and categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

Espèce

-0.72

ValueStyle

-0.65

enumi

-0.65

AndEndTag

-0.64

SuppressMessage

-0.62

+#+#

-0.59

addPreferredGap

-0.54

GraphicsUnit

-0.54

TagMode

-0.54

intellij

-0.54

POSITIVE LOGITS

 resourceCulture

0.86

 dolayı

0.66

Демографія

0.56

 ExecuteAsync

0.54

 OFDb

0.54

providedIn

0.53

 ComVisible

0.52

intios

0.52

IndentedString

0.51

chappement

0.49

Activations Density 0.102%

phrases related to questions, lists, and categories

No Comments

No Known Activations