INDEX

Explanations

phrases related to physical protrusions or extensions

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

脚注の使い方

-0.56

PyTuple

-0.52

Captor

-0.52

newswire

-0.50

uitable

-0.49

 SUDOC

-0.48

 setInterval

-0.48

StoryboardSegue

-0.46

ाव

-0.45

Initializable

-0.45

POSITIVE LOGITS

 AssemblyTitle

0.77

 propOrder

0.67

Efq

0.66

 protruding

0.66

 cref

0.61

://$

0.60

 protr

0.59

ussch

0.57

цездатний

0.56

entuh

0.56

Activations Density 0.449%

phrases related to physical protrusions or extensions

No Comments

No Known Activations