INDEX

Explanations

discussions about personal experiences and memories

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

dafx

-0.52

 Cæsar

-0.49

 Monfieur

-0.49

 currently

-0.48

Referencer

-0.47

onActivityResult

-0.47

 Majefty

-0.46

 Jefus

-0.46

 allgemein

-0.46

 Reſ

-0.45

POSITIVE LOGITS

tagHelperRunner

0.81

MethodManager

0.76

########.

0.67

JspWriter

0.60

 الرياضيه

0.59

__]

0.59

ÁRIO

0.59

Източници

0.57

entile

0.57

Hilarious

0.57

Activations Density 0.304%

discussions about personal experiences and memories

No Comments

No Known Activations