INDEX

Explanations

content relating to government investigations and claims of corruption

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

FunctionFlags

-0.52

őd

-0.50

labelledby

-0.49

BackStack

-0.48

RectangleBorder

-0.47

 noexcept

-0.47

 rechange

-0.47

PrototypeOf

-0.47

 AssemblyProduct

-0.46

 دیکھیے

-0.46

POSITIVE LOGITS

 falsehood

1.33

 untrue

1.29

 false

1.22

 misinformation

1.19

 lies

1.17

 inaccurate

1.09

 inaccuracies

1.07

lie

1.06

 fabricated

1.05

 rumor

1.04

Activations Density 0.952%

content relating to government investigations and claims of corruption

No Comments

No Known Activations