INDEX

Explanations

references to individuals and their roles in discussions or arguments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.41.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

 utafitiHapana

-0.46

ValueStyle

-0.45

Descripció

-0.42

UnsafeEnabled

-0.38

Tell

-0.37

 ху

-0.37

BeginInit

-0.37

astéroïdes

-0.36

 verkla

-0.36

انتهای

-0.36

POSITIVE LOGITS

 mentioned

1.23

 mention

1.23

 touched

1.14

 mentions

1.12

 mentioning

1.10

 alluded

1.04

 Mention

0.98

mention

0.98

 mencionó

0.97

 Mentioned

0.96

Activations Density 0.681%

references to individuals and their roles in discussions or arguments

No Comments

No Known Activations