INDEX

Explanations

references to time, specifically relating to the term "late."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/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.21.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

#+#

-0.52

 snart

-0.50

IPAddress

-0.49

nskap

-0.49

reu

-0.47

 recién

-0.46

atini

-0.45

WQS

-0.45

modities

-0.44

 Marit

-0.44

POSITIVE LOGITS

 LATE

0.89

comers

0.88

 lamented

0.86

 Late

0.83

 afternoon

0.83

LATE

0.83

 late

0.82

Late

0.81

comer

0.77

 stages

0.75

Activations Density 0.078%

references to time, specifically relating to the term "late."

No Comments

No Known Activations