INDEX

Explanations

instances of the word "again" in various forms and contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

-0.90

 Hale

-0.67

€¢

-0.63

 Hartford

-0.63

स्य

-0.62

BRC

-0.61

".$_

-0.61

Iy

-0.60

 fers

-0.60

Iy

-0.59

POSITIVE LOGITS

TestingModule

0.81

 again

0.81

 numberWith

0.81

jsdelivr

0.80

 Again

0.77

 AGAIN

0.76

AGAIN

0.76

igshid

0.75

Again

0.75

0.73

Activations Density 0.036%

instances of the word "again" in various forms and contexts

No Comments

No Known Activations