INDEX

Explanations

references to sources and insider information in a news context

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

Attribution of information to anonymous sources

np_acts-logits-general · gemini-2.0-flash

source said, told, or shared

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

AddTagHelper

-0.68

$_['

-0.64

AndroidJUnit

-0.60

PhysRevD

-0.58

TestTools

-0.55

SBATCH

-0.51

RunWith

-0.50

moveToFirst

-0.50

Attached

-0.48

faccia

-0.47

POSITIVE LOGITS

 sources

0.77

 Sources

0.73

 insiders

0.68

Sources

0.67

 source

0.63

:][

0.62

AsUp

0.61

 fonte

0.60

 fuentes

0.60

 insider

0.59

Activations Density 0.095%

references to sources and insider information in a news context

Attribution of information to anonymous sources

source said, told, or shared

No Comments

No Known Activations