INDEX

Explanations

references to political parties and their activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Especies

-0.45

 neighbor

-0.43

 neighbors

-0.43

 Nachbarn

-0.41

 Neighbors

-0.40

 övers

-0.40

neighbor

-0.40

XtraGrid

-0.40

 operator

-0.39

 Operator

-0.39

POSITIVE LOGITS

 party

1.46

party

1.26

 Party

1.26

PARTY

1.22

Party

1.21

 PARTY

1.21

 caucus

1.02

 Partei

0.98

 Caucus

0.92

 political

0.89

Activations Density 0.238%

references to political parties and their activities

No Comments

No Known Activations