INDEX

Explanations

locations and settings related to personal spaces and interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

enumi

-0.63

 fundamentally

-0.54

WireFormatLite

-0.52

proken

-0.51

dAtA

-0.51

ífero

-0.50

dorff

-0.49

verture

-0.49

日在

-0.49

omenta

-0.49

POSITIVE LOGITS

#+#

0.59

 فريبيس

0.58

pédie

0.55

 lenker

0.53

.*")]

0.52

bootstrapcdn

0.50

CppCodeGen

0.50

konferenz

0.48

 room

0.48

 sạn

0.48

Activations Density 0.405%

locations and settings related to personal spaces and interactions

No Comments

No Known Activations