INDEX

Explanations

numeric values and codes related to data or programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 myſelf

-1.04

 Reſ

-0.95

 ―――――

-0.89

 Monfieur

-0.85

rungsseite

-0.83

 itſelf

-0.81

 Theſe

-0.80

 ་་

-0.80

 Anſ

-0.80

 crdi

-0.79

POSITIVE LOGITS

fal

0.64

<eos>

0.62

0.57

fycat

0.51

fil

0.46

 pattern

0.46

fromnode

0.46

0.45

 major

0.45

ze

0.45

Activations Density 0.529%

numeric values and codes related to data or programming

No Comments

No Known Activations