INDEX

Explanations

references to methods of evidence and representation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

XmlAccessorType

-0.53

 Pera

-0.52

竟然

-0.51

tså

-0.48

canestro

-0.48

ispiele

-0.46

berra

-0.46

 sogar

-0.46

gregor

-0.45

 especially

-0.44

POSITIVE LOGITS

而已

0.74

 незавершена

0.69

 thôi

0.69

AndEndTag

0.66

罢了

0.66

CppCodeGen

0.65

 المعيارى

0.65

ContentAsync

0.64

NameInMap

0.64

 propOrder

0.64

Activations Density 0.561%

references to methods of evidence and representation

No Comments

No Known Activations