INDEX

Explanations

terms related to operational modes or settings

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 tartalomajánló

-0.76

клопе

-0.76

 '=',

-0.70

 Theſe

-0.70

Questão

-0.70

devamını

-0.68

WriteBarrier

-0.68

orithms

-0.67

VERTISEMENT

-0.67

 Reſ

-0.66

POSITIVE LOGITS

Mode

0.79

mode

0.77

 mode

0.75

 Mode

0.67

 modes

0.64

context

0.63

MODE

0.63

ong

0.62

ol

0.62

 circumstances

0.59

Activations Density 0.071%

terms related to operational modes or settings

No Comments

No Known Activations