INDEX

Explanations

expressions of nostalgia and appreciation related to past experiences with media, particularly anime

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

us

-0.54

 conmigo

-0.53

our

-0.52

“

-0.44

 вас

-0.43

 abgerufen

-0.41

 yourself

-0.41

me

-0.41

私たち

-0.40

it

-0.40

POSITIVE LOGITS

 Lately

0.97

 disambiguazione

0.97

 Italijanski

0.96

 lately

0.94

 Prefer

0.90

AsUp

0.89

 prefer

0.88

 preferring

0.88

ThroughAttribute

0.87

ỡng

0.84

Activations Density 0.183%

expressions of nostalgia and appreciation related to past experiences with media, particularly anime

No Comments

No Known Activations