INDEX

Explanations

words and phrases related to death, family, relationships, sci-fi, space, or collapse

oai_token-act-pair · gemini-2.0-flash

death or loss

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 thoſe

-0.63

 myſelf

-0.55

 synag

-0.54

 himſelf

-0.49

 reciprocal

-0.48

 theſe

-0.48

 antem

-0.48

atum

-0.47

 another

-0.47

 repres

-0.47

POSITIVE LOGITS

 AssemblyCulture

0.81

MigrationBuilder

0.81

MLLoader

0.72

RenderAtEndOf

0.68

DockStyle

0.66

findpost

0.64

tvguidetime

0.61

 '\\;'

0.60

+#+#

0.60

ImageContext

0.59

Activations Density 0.322%

words and phrases related to death, family, relationships, sci-fi, space, or collapse

death or loss

No Comments

No Known Activations