INDEX

Explanations

actions that demonstrate a sense of initiating or starting something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

continuing

-0.62

 venait

-0.60

continued

-0.59

odzi

-0.59

 gelang

-0.58

 qualunque

-0.58

 Frisch

-0.56

remaining

-0.56

 actuels

-0.55

 déclar

-0.55

POSITIVE LOGITS

Referències

0.82

ViewFeatures

0.82

 المعيارى

0.81

MessageTagHelper

0.78

 دیکھیے

0.71

 ProtoMessage

0.68

WireFormatLite

0.65

TagMode

0.64

saraba

0.64

NameInMap

0.63

Activations Density 0.088%

actions that demonstrate a sense of initiating or starting something

No Comments

No Known Activations