INDEX

Explanations

patterns related to code or programming syntax

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

 litté

-0.65

ങ്

-0.62

 Wikiseite

-0.56

 AssemblyTitle

-0.53

 Merv

-0.52

Byd

-0.52

совая

-0.51

WHE

-0.49

nuc

-0.48

ík

-0.48

POSITIVE LOGITS

aarrggbb

0.74

mybatisplus

0.73

xffffffff

0.67

️⃣

0.66

__(/*!

0.66

⋙

0.65

Jeografia

0.65

//

0.65

 Schre

0.65

GRANTED

0.63

Activations Density 0.015%

patterns related to code or programming syntax

No Comments

No Known Activations