INDEX

Explanations

terms related to filtering processes and techniques

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 pyruvate

-0.95

 متعلقه

-0.89

ymce

-0.87

onedDateTime

-0.87

contentLoaded

-0.84

 navideños

-0.84

samt

-0.83

 debout

-0.81

Initializable

-0.80

 ReactDOM

-0.79

POSITIVE LOGITS

 filter

3.38

 filters

3.20

 Filter

3.17

filter

3.09

Filter

3.08

 Filters

2.92

 FILTER

2.79

filters

2.69

FILTER

2.65

Filters

2.64

Activations Density 0.083%

terms related to filtering processes and techniques

No Comments

No Known Activations