INDEX

Explanations

references to customers and customer service

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Theſe

-1.21

Efq

-1.10

 itſelf

-1.05

parsedMessage

-1.03

MessageTagHelper

-1.03

^(@)

-1.02

 myſelf

-1.02

 doubtnut

-0.99

 Beſ

-0.98

 whoſe

-0.97

POSITIVE LOGITS

 customer

0.68

ster

0.59

an

0.58

per

0.58

el

0.55

 Customer

0.55

tic

0.54

Activations Density 0.148%

references to customers and customer service

No Comments

No Known Activations