INDEX

Explanations

phrases expressing gratitude or acknowledgments in a research context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

ruhe

-0.69

PhysRevLett

-0.65

-0.58

sendStatus

-0.55

<<=

-0.54

Дереккөздер

-0.52

躇

-0.52

 Portail

-0.51

หวัด

-0.51

medy

-0.51

POSITIVE LOGITS

ANTLR

0.61

tagHelperRunner

0.60

DataBinding

0.59

 Meksiku

0.55

AndEndTag

0.53

StoryboardSegue

0.52

 invokingState

0.50

Sag

0.48

esgue

0.47

SequentialGroup

0.47

Activations Density 0.235%

phrases expressing gratitude or acknowledgments in a research context

No Comments

No Known Activations