INDEX

Explanations

occurrences of the word "Or" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.34.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

 autorytatywna

-0.75

tvguidetime

-0.64

jarati

-0.55

UnitTesting

-0.47

.}~\

-0.47

 समीक्षाओं

-0.45

 respeito

-0.44

Gambas

-0.42

 Photocase

-0.42

สือ

-0.42

POSITIVE LOGITS

Or

0.79

Or

0.68

tagHelperRunner

0.65

OR

0.62

 Ор

0.56

setVerticalGroup

0.50

 createSlice

0.45

Билгалдахарш

0.45

Else

0.44

léans

0.43

Activations Density 0.193%

occurrences of the word "Or" in various contexts

No Comments

No Known Activations