INDEX

Explanations

features and functions related to accessibility and technology in various contexts

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

:]:

-0.45

BaseType

-0.45

 виправивши

-0.43

 estat

-0.43

-0.42

↵↵

-0.42

...

-0.41

+='

-0.41

 endl

-0.40

 resign

-0.40

POSITIVE LOGITS

InputBorder

0.98

MethodManager

0.98

WebVitals

0.95

 BIBSYS

0.87

WithIOException

0.84

Vidite

0.84

OGND

0.83

multer

0.81

prefixer

0.81

乓

0.78

Activations Density 0.998%

features and functions related to accessibility and technology in various contexts

No Comments

No Known Activations