INDEX

Explanations

primarily finds future tense statements passive voice or announcements, but also finds instances of "action" and "year".

oai_token-act-pair · gemini-2.0-flash

be

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

rungsseite

-0.56

 betweenstory

-0.52

we

-0.48

mio

-0.47

tagHelperRunner

-0.46

дца

-0.45

pas

-0.45

вёр

-0.45

 عد

-0.43

stan

-0.43

POSITIVE LOGITS

 Roskov

0.79

NUMX

0.73

tonode

0.71

esgue

0.70

jsonwebtoken

0.69

pirable

0.69

 NDEBUG

0.68

principalTable

0.67

UIControlState

0.66

getDoctrine

0.65

Activations Density 1.918%

primarily finds future tense statements passive voice or announcements, but also finds instances of "action" and "year".

be

No Comments

No Known Activations