INDEX

Explanations

phrases that indicate evidence or demonstration of a concept or phenomenon

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

autoreleasepool

-0.38

XmlAccessorType

-0.36

 actionPerformed

-0.36

TryDecodeAsNil

-0.35

PropertyChanging

-0.35

RegressionTest

-0.35

MessageState

-0.35

unters

-0.34

styleType

-0.33

 telefónica

-0.33

POSITIVE LOGITS

 showing

0.82

 Showing

0.78

showing

0.73

Showing

0.66

Diwedd

0.62

 SHOWING

0.62

 mostrando

0.62

Portale

0.60

 Devices

0.60

 незавершена

0.59

Activations Density 0.330%

phrases that indicate evidence or demonstration of a concept or phenomenon

No Comments

No Known Activations