INDEX

Explanations

comparative phrases highlighting differences in quantity, size, or performance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 unico

-0.57

BARA

-0.57

 ratio

-0.54

seud

-0.53

Nou

-0.53

 Renewal

-0.52

hingga

-0.51

woordig

-0.51

unico

-0.50

yra

-0.50

POSITIVE LOGITS

AddTagHelper

1.00

TemporalType

0.84

istoitu

0.75

 betweenstory

0.73

 Lokales

0.61

 protoimpl

0.61

 Paglinawan

0.61

 RoutedEventArgs

0.60

writeFieldEnd

0.60

ActionCreators

0.58

Activations Density 0.439%

comparative phrases highlighting differences in quantity, size, or performance

No Comments

No Known Activations