INDEX

Explanations

terms related to the concept of "interests."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

BagLayout

-0.70

 jLabel

-0.65

 pleaſure

-0.63

 Ephesus

-0.54

änomen

-0.53

 burs

-0.53

={({

-0.53

 perfons

-0.53

jestel

-0.52

>--}}

-0.52

POSITIVE LOGITS

 benefit

0.68

ütfen

0.59

benefit

0.59

-------------</

0.59

 kepentingan

0.58

 benefits

0.58

 Benefit

0.57

 sebaiknya

0.57

 préférable

0.55

 sauvegarde

0.55

Activations Density 0.324%

terms related to the concept of "interests."

No Comments

No Known Activations