INDEX

Explanations

phrases indicating interdependence or connections between entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Valdés

-0.57

MarshalTo

-0.57

CodeAttribute

-0.55

TagMode

-0.54

docx

-0.53

Tikang

-0.51

下载附件

-0.51

 ModelAndView

-0.51

單位

-0.50

 GBIF

-0.50

POSITIVE LOGITS

 elkaar

0.84

 einander

0.73

 nhau

0.64

 PHPUnit

0.64

(&:

0.61

 mutually

0.60

 untere

0.60

 друг

0.60

お互

0.59

Datuak

0.58

Activations Density 0.141%

phrases indicating interdependence or connections between entities

No Comments

No Known Activations