INDEX

Explanations

phrases related to specific types of objects or components

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

Jegyzetek

-0.75

BeginContext

-0.74

İstinadlar

-0.71

ंदीखरीदारी

-0.66

enumi

-0.66

 CreateTagHelper

-0.65

 pinulongan

-0.64

 Wikimedijinoj

-0.64

TestingModule

-0.64

bootstrapcdn

-0.63

POSITIVE LOGITS

invokeLater

0.62

 legislation

0.60

 stuff

0.59

 software

0.52

musik

0.49

 music

0.49

 coursework

0.47

gettime

0.47

 excellent

0.47

stuff

0.46

Activations Density 0.881%

phrases related to specific types of objects or components

No Comments

No Known Activations