INDEX

Explanations

occurrences of the word "ot"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Efq

-0.72

 Reſ

-0.65

 Theſe

-0.65

 مشين

-0.64

 Spree

-0.60

ſelf

-0.60

atimes

-0.59

 Houſe

-0.59

readObject

-0.58

DispatchToProps

-0.57

POSITIVE LOGITS

Ot

0.74

ot

0.73

==

0.65

==

0.62

 surla

0.61

ot

0.60

()==

0.60

===

0.59

 الحره

0.58

OGND

0.58

Activations Density 0.222%

occurrences of the word "ot"

No Comments

No Known Activations