INDEX

Explanations

references to binary data

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 LoggerFactory

-0.70

GoogleApiClient

-0.64

fjspx

-0.63

gonic

-0.63

FetchType

-0.63

 Johnnie

-0.60

paksa

-0.59

AppComponent

-0.58

ColumnInfo

-0.57

 éprou

-0.57

POSITIVE LOGITS

 Phys

0.91

*{

0.85

 Liability

0.74

Liability

0.73

 liability

0.66

 phys

0.65

mali

0.65

Binary

0.64

Phys

0.64

 LIABILITY

0.64

Activations Density 0.051%

references to binary data

No Comments

No Known Activations