INDEX

Explanations

dates, especially those related to events or occurrences

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gb

-0.68

</em>

-0.68

 Graff

-0.67

ge

-0.66

="">

-0.65

pol

-0.65

lege

-0.64

orge

-0.64

 meta

-0.62

zam

-0.61

POSITIVE LOGITS

 Wednesday

1.79

Wednesday

1.73

 Thursday

1.69

 Tuesday

1.68

Thursday

1.66

Tuesday

1.58

 Wednesdays

1.52

 Thursdays

1.49

 Monday

1.47

 Tuesdays

1.46

Activations Density 0.033%

dates, especially those related to events or occurrences

No Comments

No Known Activations