INDEX

Explanations

names or references to specific authors or researchers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

enumi

-0.69

قایناق‌لار

-0.64

rungsseite

-0.62

 myſelf

-0.62

 vulgaires

-0.58

 Waray

-0.58

 congratulate

-0.58

 cobalt

-0.57

UIControlState

-0.57

 Caro

-0.56

POSITIVE LOGITS

der

0.79

den

0.59

tagens

0.51

 GenerationType

0.50

migrationBuilder

0.49

 Gogh

0.49

illin

0.48

comy

0.48

Der

0.47

ities

0.45

Activations Density 0.122%

names or references to specific authors or researchers

No Comments

No Known Activations