INDEX

Explanations

negative phrases that have to do with conformity

oai_token-act-pair · gemini-2.0-flash

repetition and routine

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

ImageContext

-0.78

TestingModule

-0.74

UrlResolution

-0.67

 BoxFit

-0.66

 שוליים

-0.64

 FetchType

-0.63

WritableDatabase

-0.62

 avoient

-0.61

parsedMessage

-0.60

styleable

-0.59

POSITIVE LOGITS

 routine

1.02

 rote

0.83

 Routine

0.82

rut

0.77

routine

0.76

 repetitive

0.75

 repeating

0.73

 mechanically

0.73

Routine

0.71

ROUTINE

0.71

Activations Density 1.748%

negative phrases that have to do with conformity

repetition and routine

No Comments

No Known Activations