INDEX

Explanations

instances of changing ideas or switching between them.

oai_token-act-pair · gemini-2.0-flash

changed

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

 kasarigan

-0.55

IOLOGY

-0.53

HttpPut

-0.50

 &___

-0.48

 alun

-0.48

 <>",

-0.47

 Comentarios

-0.46

市镇

-0.44

 مشارکت‌کنندگان

-0.43

CppMethod

-0.43

POSITIVE LOGITS

enumi

0.72

 useStyles

0.69

<bos>

0.60

BeginInit

0.60

 AssemblyCulture

0.60

 متعلقه

0.58

IsMutable

0.58

IntoConstraints

0.57

 ['./

0.56

 direction

0.54

Activations Density 1.512%

instances of changing ideas or switching between them.

changed

No Comments

No Known Activations