INDEX

Explanations

varied forms of the word "that" and related phrases indicating existence or relevance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

 this

-0.57

This

-0.56

 This

-0.52

 itong

-0.48

this

-0.47

THIS

-0.45

 tavola

-0.45

 birbir

-0.45

Este

-0.44

 Este

-0.44

POSITIVE LOGITS

 ComVisible

0.99

OGND

0.94

 Those

0.82

 THOSE

0.78

Those

0.78

EditorBrowsable

0.76

 That

0.75

Tembelea

0.75

those

0.74

__*/

0.74

Activations Density 0.420%

varied forms of the word "that" and related phrases indicating existence or relevance

No Comments

No Known Activations