INDEX

Explanations

multiple separate patterns, but is largely related to reaching out to others to communicate or follow up.

oai_token-act-pair · gemini-2.0-flash

contacting someone

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

ValueStyle

-0.87

исленность

-0.85

évaluateur

-0.83

awtextra

-0.76

QMetaType

-0.76

MigrationBuilder

-0.74

WebVitals

-0.74

^(@)

-0.72

AddHtmlAttribute

-0.71

 itſelf

-0.71

POSITIVE LOGITS

andre

0.45

 base

0.45

0.44

in

0.41

re

0.40

TableField

0.40

基

0.39

 али

0.38

atr

0.37

 officer

0.37

Activations Density 0.587%

multiple separate patterns, but is largely related to reaching out to others to communicate or follow up.

contacting someone

No Comments

No Known Activations