INDEX

Explanations

the word "get" and its variations

oai_token-act-pair · gemini-2.0-flash

variances in difficulty or quality

np_token-act-pair-logits · gpt-4o-mini

get

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 الحره

-0.77

SourceChecksum

-0.75

Efq

-0.75

StoryboardSegue

-0.70

UrlResolution

-0.66

Enllaces

-0.64

Eſ

-0.64

ThemeOverlay

-0.63

 kaynağından

-0.63

DeleteBehavior

-0.63

POSITIVE LOGITS

 easier

0.52

me

0.49

 harder

0.49

 tricky

0.48

 worse

0.48

 pretty

0.48

 MORE

0.46

 tougher

0.46

arko

0.46

 nakalista

0.45

Activations Density 0.495%

the word "get" and its variations

variances in difficulty or quality

get

No Comments

No Known Activations