INDEX

Explanations

phrases related to upcoming actions or planned discussions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

#+#

-0.69

 autorytatywna

-0.54

 artesanales

-0.50

complexType

-0.50

routeProvider

-0.49

wpi

-0.47

ními

-0.47

setHeader

-0.47

 false

-0.47

mappedBy

-0.46

POSITIVE LOGITS

RegressionTest

0.67

 digress

0.64

ंदीखरीदारी

0.63



0.63

Rujuakan

0.57

putan

0.57

hubanes

0.57

Kariera

0.57

\}_{

0.54

ここでは

0.54

Activations Density 1.005%

phrases related to upcoming actions or planned discussions

No Comments

No Known Activations