INDEX

Explanations

phrases indicating requests for information or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

jsonwebtoken

-0.63

 estekak

-0.56

>>;

-0.53

 transfieras

-0.52

 jspb

-0.51

stylers

-0.50

])*

-0.49

]]:

-0.48

 okuyayım

-0.48

 indoss

-0.48

POSITIVE LOGITS

StoryboardSegue

0.62

المكان

0.58

 AVAILABLE

0.57

cual

0.55

 available

0.52

viale

0.52

RegressionTest

0.51

unch

0.51

hra

0.51

 cser

0.51

Activations Density 0.169%

phrases indicating requests for information or services

No Comments

No Known Activations