INDEX

Explanations

references to numerical values or comparisons in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 للاسماء

-0.46

heiro

-0.46

slidesPer

-0.45

رشف

-0.43

 then

-0.43

 <<<<<<<<<<<<<<

-0.42

了一

-0.42

MLLoader

-0.41

末

-0.41

aderie

-0.39

POSITIVE LOGITS

aka

0.76

 equivalently

0.74

WireFormatLite

0.74

いわゆる

0.66

AKA

0.65

AKA

0.65

 &___

0.64

andidaten

0.64

つまり

0.63

 ujednoznacz

0.63

Activations Density 0.399%

references to numerical values or comparisons in various contexts

No Comments

No Known Activations