INDEX

Explanations

punctuation marks used to denote pauses or breaks in text

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

 Penna

-0.69

Parcelize

-0.68

(_,

-0.67

listdir

-0.67

,…

-0.66

 AppBar

-0.64

,...,

-0.64

AccessorTable

-0.64

żeń

-0.63

Lue

-0.63

POSITIVE LOGITS

but

0.77

 although

0.73

 потому

0.70

 thus

0.69

 which

0.67

 though

0.65

 thereby

0.64

úrate

0.63

 therefore

0.63

 hence

0.62

Activations Density 0.695%

punctuation marks used to denote pauses or breaks in text

No Comments

No Known Activations