INDEX

Explanations

occurrences of the words "we", "are", "was", "been" and "am".

oai_token-act-pair · gemini-2.0-flash

feelings

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

mybatisplus

-0.83

Portail

-0.81

Portale

-0.75

 MainAxisSize

-0.71

enumi

-0.68

^(@)

-0.68

̓

-0.68

 pleaſure

-0.68

 endblock

-0.66

ConstraintMaker

-0.65

POSITIVE LOGITS

 concerned

0.57

 angry

0.56

 ffilmiau

0.54

 confident

0.53

 aware

0.52

 interested

0.52

 eager

0.51

 cogniz

0.51

 worried

0.50

 intrigued

0.50

Activations Density 1.190%

occurrences of the words "we", "are", "was", "been" and "am".

feelings

No Comments

No Known Activations