INDEX

Explanations

questions and phrases related to transitions or changes in narrative elements

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

FactoryBean

-0.46

Джерело

-0.43

 Nullable

-0.42

RestController

-0.42

 useState

-0.42

 column

-0.42

 ados

-0.42

Clique

-0.40

 resourceCulture

-0.40

retor

-0.39

POSITIVE LOGITS

 مرئيه

0.94

PYX

0.88

kloped

0.70

 AssemblyCulture

0.67

GIVEREF

0.67

ineno

0.65

postIndex

0.65

Personendaten

0.63

=?";

0.62

וויק

0.62

Activations Density 0.202%

questions and phrases related to transitions or changes in narrative elements

No Comments

No Known Activations