INDEX

Explanations

responses related to user queries and interactions in a customer service or support context

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

Capitalized word at the beginning of a sentence

np_acts-logits-general · gemini-2.0-flash

list item or code structure

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

 kaynağından

-0.71

 oprot

-0.68

StructEnd

-0.66

 BoxFit

-0.66

かわらず

-0.66

Portail

-0.66

 ProtoMessage

-0.66

 المعيارى

-0.64

లాలు

-0.64

fromnode

-0.63

POSITIVE LOGITS

XmlAccessType

0.68

<bos>

0.62

verwijspagina

0.59

prnewswire

0.56

twimg

0.49

ÁND

0.46

httphttps

0.46

::::::::

0.43

 (...)

0.42

Activations Density 0.776%

responses related to user queries and interactions in a customer service or support context

Capitalized word at the beginning of a sentence

list item or code structure

No Comments

No Known Activations