INDEX

Explanations

terms and numbers associated with statistical or mathematical data

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

fromCharCode

-0.81

HtmlAttribute

-0.76

 MessageBoxIcon

-0.70

 Abbot

-0.70

 Conan

-0.67

WEAR

-0.64

 Enzo

-0.64

심

-0.64

DotNetBar

-0.62

 Hester

-0.62

POSITIVE LOGITS

/***/

0.69

Parcelize

0.66

ListModule

0.65

LSM

0.64

LPS

0.63

LS

0.63

LSB

0.63

ISE

0.61

bootstrapcdn

0.61

LS

0.60

Activations Density 0.258%

terms and numbers associated with statistical or mathematical data

No Comments

No Known Activations