INDEX

Explanations

references to members of parliament or parliamentary terms

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

routeProvider

-0.58

 Carri

-0.56

ぬ

-0.53

iello

-0.52

 Lave

-0.51

 хо

-0.49

ptr

-0.49

ocat

-0.49

iddler

-0.47

~•

-0.47

POSITIVE LOGITS

MP

1.27

MPs

1.27

MP

1.24

 opinion

1.05

mp

1.00

 Opinion

0.97

opinion

0.94

 Meinung

0.92

Opinion

0.92

expandindo

0.91

Activations Density 0.035%

references to members of parliament or parliamentary terms

No Comments

No Known Activations