INDEX

Explanations

language related to future events or possibilities in both general text and programming contexts

oai_token-act-pair · gemini-2.0-flash

will

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 will

-0.69

Will

-0.69

<bos>

-0.67

will

-0.61

 Will

-0.60

WILL

-0.56

 shall

-0.55

 WILL

-0.50

 poveznice

-0.50

Aholisi

-0.47

POSITIVE LOGITS

amazonaws

0.69

internalType

0.58

期刊论文

0.54

tvguidetime

0.54

็จ

0.52

̍t

0.50

 تانيه

0.48

*)(

0.48

 lenker

0.48

CodeAnalysis

0.48

Activations Density 1.193%

language related to future events or possibilities in both general text and programming contexts

will

No Comments

No Known Activations