INDEX

Explanations

references to specific subjects or entities within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 समीक्षाएं

-0.68

 تانيه

-0.58

imageshack

-0.52

AdapterFactory

-0.51

 layui

-0.50

__;

-0.49

CardModule

-0.48

+#+#

-0.47

 يتيمه

-0.47

anho

-0.47

POSITIVE LOGITS

러한

0.70

 These

0.63

这些

0.63

These

0.62

Джерела

0.61

 ועוד

0.61

.*")]

0.60

 this

0.60

 these

0.59

這些

0.58

Activations Density 0.450%

references to specific subjects or entities within the text

No Comments

No Known Activations