INDEX

Explanations

code-related syntax and structures, specifically focusing on file operations and JSON handling

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

Code snippets and programming-related terms

np_acts-logits-general · gemini-2.0-flash

programming and network requests

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

ne

-0.51

-0.50

-0.48

Ne

-0.47

-0.46

weg

-0.44

-0.43

POSITIVE LOGITS

 betweenstory

0.88

 itſelf

0.87

 photolibrary

0.86

 Anſ

0.86

évaluateur

0.85

 Conſ

0.84

 iſt

0.84

ValueStyle

0.84

utilisons

0.83

 StatelessWidget

0.83

Activations Density 0.070%

code-related syntax and structures, specifically focusing on file operations and JSON handling

Code snippets and programming-related terms

programming and network requests

No Comments

No Known Activations