INDEX

Explanations

references to the United States or its institutions

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

 universitaria

-0.51

ⓧ

-0.51

ļi

-0.51

 gustaría

-0.50

ItemBackground

-0.49

ViewChild

-0.47

InjectAttribute

-0.47

mox

-0.47

Bakgrunnsstoff

-0.46

grafi

-0.46

POSITIVE LOGITS

choly

0.58

 INTERESAR

0.56

atecas

0.56

 SDLK

0.54

Notae

0.54

valdi

0.54

béco

0.53

getRuntime

0.53

Spl

0.52

iastes

0.52

Activations Density 0.117%

references to the United States or its institutions

No Comments

No Known Activations