INDEX

Explanations

the word "again" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

kano

-0.81

Hern

-0.68

ZI

-0.65

-0.64

Koc

-0.63

 Hale

-0.63

fect

-0.62

 fers

-0.61

 Purdy

-0.61

 отношению

-0.61

POSITIVE LOGITS

 again

1.73

Again

1.71

again

1.69

 Again

1.66

 AGAIN

1.60

AGAIN

1.48

 igjen

1.27

 novamente

1.17

 Lagi

1.08

 nuevamente

1.07

Activations Density 0.047%

the word "again" and its variations

No Comments

No Known Activations