INDEX

Explanations

requests for assistance or information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 libra

-0.60

 kasarigan

-0.52

今度は

-0.50

BnF

-0.48

yntaxException

-0.48

uki

-0.47

 المعيارى

-0.46

Allowed

-0.46

FieldNumber

-0.46

니까

-0.44

POSITIVE LOGITS

 please

1.31

please

1.05

 pleased

1.03

 Please

0.99

Kindly

0.98

 Kindly

0.96

plz

0.94

 PLEASE

0.90

pls

0.90

 bitte

0.88

Activations Density 0.087%

requests for assistance or information

No Comments

No Known Activations