INDEX

Explanations

programming constructs related to filtering and handling package options

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

bellar

-0.50

It

-0.49

And

-0.46

-0.45

To

-0.44

 plat

-0.44

 permiti

-0.44

en

-0.42

and

-0.41

If

-0.41

POSITIVE LOGITS

 AssemblyCulture

0.98

 CreateTagHelper

0.94

findpost

0.93

 myſelf

0.88

 ainfi

0.83

 feroit

0.83

OGND

0.83

 auroit

0.81

contentLoaded

0.79

 Theſe

0.79

Activations Density 0.213%

programming constructs related to filtering and handling package options

No Comments

No Known Activations