INDEX

Explanations

phrases indicating a request for help or gratitude, often related to technical issues

oai_token-act-pair · gemini-2.0-flash

numerical values in a sequence

np_token-act-pair-logits · gpt-4o-mini

programming help requests

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 '\\;'

-0.75

הערות

-0.71

Билгалдахарш

-0.68

-0.59

 ogóle

-0.58

abestanden

-0.56

TPE

-0.53

avance

-0.52

 kasarigan

-0.52

IContainer

-0.52

POSITIVE LOGITS

TargetException

0.64

 three

0.63

mockito

0.61

 five

0.59

in

0.59

six

0.59

 nine

0.58

ten

0.56

 eight

0.54

 seven

0.54

Activations Density 7.567%

phrases indicating a request for help or gratitude, often related to technical issues

numerical values in a sequence

programming help requests

No Comments

No Known Activations