INDEX

Explanations

instances of specific names or technical terms associated with individuals or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 виправивши

-0.52

IVEREF

-0.50

 насељу

-0.48

 OFDb

-0.43

唉

-0.43

trường

-0.42

作者

-0.42

AnchorStyles

-0.42

íba

-0.41

บท

-0.41

POSITIVE LOGITS

 nahilalakip

0.87

 Roskov

0.83

Искәрмәләр

0.81

DebuggerNonUser

0.77

CodeAttribute

0.72

BeginContext

0.70

rungsseite

0.65

afficheront

0.64

Przypisy

0.64

 reiterated

0.63

Activations Density 0.126%

instances of specific names or technical terms associated with individuals or organizations

No Comments

No Known Activations