INDEX

Explanations

technical terminology and statistical data presented in a scientific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

rungsseite

-0.97

'{@

-0.65

pædia

-0.58

Билгалдахарш

-0.57

abetes

-0.54

ModelBuilder

-0.54

MigrationBuilder

-0.52

PASSED

-0.52

انه

-0.49

>[]

-0.49

POSITIVE LOGITS

 occasionally

1.60

 Occasionally

1.53

Occasionally

1.48

 occasional

1.28

偶尔

1.15

 sometimes

1.13

occasion

1.09

たまに

1.04

 rarely

1.04

 Rarely

1.01

Activations Density 0.418%

technical terminology and statistical data presented in a scientific context

No Comments

No Known Activations