INDEX

Explanations

mentions of hardware

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

BeginContext

-1.03

RegressionTest

-0.96

parsedMessage

-0.94

WebVitals

-0.93

ScopeManager

-0.92

 étoit

-0.90

tvguidetime

-0.89

AsUp

-0.88

 méri

-0.87

RetentionPolicy

-0.86

POSITIVE LOGITS

 hardware

2.04

 Hardware

1.89

Hardware

1.80

hardware

1.76

HARDWARE

1.38

硬件

1.25

HW

1.02

HW

0.95

hw

0.93

 HARD

0.89

Activations Density 0.073%

mentions of hardware

No Comments

No Known Activations