INDEX

Explanations

mentions of significant results or effects in research studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

AdapterView

-0.67

 AdapterView

-0.66

RLock

-0.65

bra

-0.64

la

-0.64

ap

-0.63

ো

-0.63

try

-0.62

on

-0.62

AspNetCore

-0.62

POSITIVE LOGITS

ificance

1.52

ificant

1.41

ificantly

1.39

BibitemShut

1.23

']))

1.11

 SIGNIFIC

1.08

 significant

1.05

Significant

1.03

^(@)

1.03

 signific

1.03

Activations Density 0.145%

mentions of significant results or effects in research studies

No Comments

No Known Activations