INDEX

Explanations

words and phrases that connote influence or change

oai_token-act-pair · gemini-2.0-flash

virtual and influence

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

undering

-0.69

UGHS

-0.63

rshire

-0.63

 Assignee

-0.63

rophi

-0.62

oplastic

-0.60

ADOS

-0.60

ochial

-0.59

mopol

-0.59

itarian

-0.58

POSITIVE LOGITS

<bos>

1.34

AndEndTag

0.76

 pendapat

0.65

↵↵

0.64

bootstrapcdn

0.62

 cerimonia

0.62

 judiciaire

0.61

 médicale

0.60

 proprietario

0.59

 gethan

0.58

Activations Density 1.979%

words and phrases that connote influence or change

virtual and influence

No Comments

No Known Activations