INDEX

Explanations

statements including source, opinion/belief, and a "that" clause; or references to political policy

oai_token-act-pair · gemini-2.0-flash

believe

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

Stating an opinion/belief

np_max-act-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

 kaynağından

-0.59

Geschiedenis

-0.50

 predicted

-0.50

agissait

-0.49

 allegedly

-0.48

ikations

-0.47

EndInit

-0.46

 écoulé

-0.46

الدراسه

-0.45

存于互联网档案馆

-0.45

POSITIVE LOGITS

AndEndTag

0.72

PRF

0.60

 nakalista

0.59

rrggbb

0.58

Rhestr

0.57

 présent

0.56

fficients

0.56

 esimer

0.54

addCriterion

0.52

TintMode

0.52

Activations Density 1.216%

statements including source, opinion/belief, and a "that" clause; or references to political policy

believe

Stating an opinion/belief

No Comments

No Known Activations