INDEX

Explanations

terms related to something being "known" or "commonly known."

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

łec

-0.75

כשיו

-0.63

Dux

-0.63

 dalamnya

-0.60

yczą

-0.59

sps

-0.59

 Datenschutzer

-0.58

 Butterworth

-0.58

要不要

-0.57

Frey

-0.56

POSITIVE LOGITS

 known

3.18

 Known

2.84

known

2.79

 KNOWN

2.73

Known

2.73

KNOWN

2.24

 conocido

2.00

 conocida

1.96

 connue

1.91

 conhecido

1.89

Activations Density 0.050%

terms related to something being "known" or "commonly known."

No Comments

No Known Activations