INDEX

Explanations

references to legal proceedings and analyses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

-0.50

ाद

-0.48

-0.46

derna

-0.45

…

-0.44

éta

-0.44

↵↵

-0.43

POSITIVE LOGITS

 Majefty

1.06

Efq

1.03

 itſelf

0.93

 himſelf

0.88

 fubject

0.86

ſelf

0.86

 myſelf

0.85

 JpaRepository

0.85

 ſtate

0.84

Eſ

0.84

Activations Density 0.398%

references to legal proceedings and analyses

No Comments

No Known Activations