INDEX

Explanations

elements that indicate potential errors or issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

Geplaatst

-0.95

styleType

-0.81

twimg

-0.72

Revenir

-0.72

 Paglinawan

-0.70

adaptiveStyles

-0.68

DrawerToggle

-0.68

igshid

-0.68

Архівовано

-0.68

 presenti

-0.67

POSITIVE LOGITS

0.73

0.58

ianum

0.53

0.51

Mab

0.49

0.48

xticks

0.45

 quant

0.45

Activations Density 0.447%

elements that indicate potential errors or issues

No Comments

No Known Activations