INDEX

Explanations

words related to job interviews and/or applying for something

oai_token-act-pair · gemini-2.0-flash

quality

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_18/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.18.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

CPtr

-0.63

ragos

-0.62

verwijspagina

-0.60

Билгалдахарш

-0.60

-0.59

photobucket

-0.59

 BoxFit

-0.57

BeginContext

-0.57

 räum

-0.56

autorest

-0.55

POSITIVE LOGITS

 quality

0.86

quality

0.85

QUALITY

0.79

Quality

0.79

 QUALITY

0.75

 Quality

0.75

 qualité

0.75

 calidad

0.71

 candidates

0.65

 qualified

0.65

Activations Density 1.192%

words related to job interviews and/or applying for something

quality

No Known Activations