INDEX

Explanations

temporal phrases indicating time periods or durations

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

tanleria

-0.57

board

-0.54

éndolo

-0.53

 satunya

-0.52

={<

-0.51

 jLabel

-0.51

("")

-0.51

 Lars

-0.50

åg

-0.49

庁

-0.49

POSITIVE LOGITS

 동안

0.69

 Selama

0.66

 تضيفلها

0.65

 since

0.65

 recent

0.64

 طی

0.64

Selama

0.63

tinyos

0.63

 year

0.61

 løpet

0.60

Activations Density 0.277%

temporal phrases indicating time periods or durations

No Comments

No Known Activations