INDEX

Explanations

words related to suggestion or indication

oai_token-act-pair · gemini-2.0-flash

ured

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 Caption

-0.58

Reparto

-0.57

ArgsConstructor

-0.56

alik

-0.56

amental

-0.55

cketed

-0.55

HtmlAttribute

-0.55

PENT

-0.54

liability

-0.53

Przeczytaj

-0.53

POSITIVE LOGITS

 INDIC

1.00

 indicating

0.96

 indicate

0.94

 indications

0.93

 indicates

0.93

 Indicates

0.90

INDIC

0.89

<bos>

0.88

 suggesting

0.86

Indicates

0.86

Activations Density 0.595%

words related to suggestion or indication

ured

No Comments

No Known Activations