INDEX

Explanations

sections of text that contain lists or enumerations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

WebVitals

-0.72

Personendaten

-0.64

IVEREF

-0.62

bootstrapcdn

-0.59

ArrowToggle

-0.54

IntoConstraints

-0.53

Portály

-0.51

 <=",

-0.46

Vidite

-0.46

 hadapan

-0.45

POSITIVE LOGITS

 second

2.46

 secondly

2.46

 Secondly

2.33

Secondly

2.20

second

2.18

Second

2.15

 Second

2.10

 SECOND

1.97

SECOND

1.82

 segundo

1.81

Activations Density 0.746%

sections of text that contain lists or enumerations

No Comments

No Known Activations