INDEX

Explanations

points emphasizing the importance of research or findings

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

between or among

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

Rhestr

-0.51

DateTimeField

-0.46

AutoField

-0.43

main

-0.42

brew

-0.42

 liabilities

-0.40

ccd

-0.40

gql

-0.40

 astronauts

-0.40

LHC

-0.40

POSITIVE LOGITS

 among

1.18

among

1.15

 parmi

1.12

 amongst

1.05

 Among

1.03

 wśród

1.00

Among

0.99

 AMONG

0.99

 Amongst

0.94

其中

0.91

Activations Density 0.022%

points emphasizing the importance of research or findings

between or among

No Comments

No Known Activations