INDEX

Explanations

elements related to HTTP requests and responses in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

in

-0.71

 still

-0.69

to

-0.65

 will

-0.61

im

-0.60

at

-0.59

no

-0.58

is

-0.58

-0.57

POSITIVE LOGITS

Efq

1.07

 myſelf

1.00

httphttps

1.00

تقاوى

0.97

 Houſe

0.97

 للمعارف

0.97

 Jefus

0.96

 Chriftian

0.95

bootstrapcdn

0.94

 صوتيه

0.93

Activations Density 0.099%

elements related to HTTP requests and responses in a programming context

No Comments

No Known Activations