INDEX

Explanations

emotional or impactful expressions related to thinking and description

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

CrossRef

-0.46

льше

-0.46

Välislingid

-0.44

ちな

-0.44

 preference

-0.43

意外と

-0.43

 intéressant

-0.43

пак

-0.43

 plaît

-0.41

 interés

-0.41

POSITIVE LOGITS

 indescribable

0.95

 unimaginable

0.92

 unbelievable

0.90

 unspeakable

0.84

Incredible

0.82

 incredible

0.81

 indescri

0.80

 Incredible

0.79

msgTypes

0.79

 unspeak

0.76

Activations Density 0.203%

emotional or impactful expressions related to thinking and description

No Comments

No Known Activations