INDEX

Explanations

words and phrases comparing two unrelated items or concepts by using transition words

oai_token-act-pair · gemini-2.0-flash

unidentifiable words/jargon

np_token-act-pair-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

'])){

-0.53

 difference

-0.48

 differences

-0.48

Externé

-0.47

toBeDefined

-0.46

transQ

-0.46

'])->

-0.45

 Leck

-0.44

elif

-0.44

ību

-0.43

POSITIVE LOGITS

ScopeManager

0.71

UpInside

0.69

InitVars

0.63

 fathoms

0.61

ьаж

0.61

 gynhyrchwyd

0.60

GraphicsUnit

0.60

adaptiveStyles

0.59

MessageTagHelper

0.56

Tembelea

0.56

Activations Density 7.936%

words and phrases comparing two unrelated items or concepts by using transition words

unidentifiable words/jargon

No Comments

No Known Activations